{
  "benchmark_line": "gamebench2",
  "comparability_tuples": [
    {
      "evaluation_family": "codegen_public_benchmark",
      "rating_method": "sequential_elo",
      "reasoning_effort": "balanced",
      "results_cut_id": "20260910_111653",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": "20260910_111653",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": "20260910_111653",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": "20260910_111653",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": "20260910_111653",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_kind": "overall"
    }
  ],
  "generated_at": "2026-09-10T11:16:53Z",
  "public_release_id": "gb2-20260910-43fc3ba818c2",
  "results_cut_id": "gb2-20260910-43fc3ba818c2",
  "rows": [
    {
      "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
        },
        "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": 92.37884458659907,
      "contributing_entrants": null,
      "distinct_rated_opponents": 105,
      "draws": 46,
      "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": "2026-09-10T11:06:04Z",
      "losses": 95,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 76.96244740112121,
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1322,
      "rating_method": "sequential_elo",
      "raw_elo": 2008.213355474128,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 92.37884458659907,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1181
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 952,
      "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
        },
        "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": 90.95955634051866,
      "contributing_entrants": null,
      "distinct_rated_opponents": 101,
      "draws": 35,
      "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": "2026-09-10T11:06:16Z",
      "losses": 60,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 68.46930350710791,
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 952,
      "rating_method": "sequential_elo",
      "raw_elo": 1984.8202093607915,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 90.95955634051866,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 857
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 953,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-6-astra:9acce95ba71bd7c5",
      "capped_draws": 9,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "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": 79.44415234078821,
      "contributing_entrants": null,
      "distinct_rated_opponents": 99,
      "draws": 115,
      "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": "2026-09-10T11:11:15Z",
      "losses": 116,
      "max_score": 95.94419593771026,
      "measured_at": null,
      "min_score": 57.36356914969686,
      "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": 953,
      "rating_method": "sequential_elo",
      "raw_elo": 1876.6272960247202,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 79.44415234078821,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 722
    },
    {
      "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
        },
        "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": 77.18422949193521,
      "contributing_entrants": null,
      "distinct_rated_opponents": 101,
      "draws": 82,
      "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": "2026-09-10T11:10:23Z",
      "losses": 171,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 52.70456806499455,
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 954,
      "rating_method": "sequential_elo",
      "raw_elo": 1872.6782855747924,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 77.18422949193521,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 701
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1595,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-sol:e615ab726629f0c0",
      "capped_draws": 7,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "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": 75.3716089885212,
      "contributing_entrants": null,
      "distinct_rated_opponents": 108,
      "draws": 112,
      "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": "2026-09-10T11:11:42Z",
      "losses": 314,
      "max_score": 95.50333681723484,
      "measured_at": null,
      "min_score": 57.6005678523054,
      "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": 1594,
      "rating_method": "sequential_elo",
      "raw_elo": 1828.5320119233652,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 75.3716089885212,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1168
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 952,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-6-astra:8883275fa81b106a",
      "capped_draws": 5,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "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": 75.3229753105928,
      "contributing_entrants": null,
      "distinct_rated_opponents": 102,
      "draws": 140,
      "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": "2026-09-10T10:58:46Z",
      "losses": 143,
      "max_score": 97.61905921533831,
      "measured_at": null,
      "min_score": 50.47588011557324,
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 952,
      "rating_method": "sequential_elo",
      "raw_elo": 1860.3760146441941,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 75.3229753105928,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 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
        },
        "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": 73.78797011506347,
      "contributing_entrants": null,
      "distinct_rated_opponents": 103,
      "draws": 123,
      "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": "2026-09-10T11:06:19Z",
      "losses": 161,
      "max_score": 89.2299699098686,
      "measured_at": null,
      "min_score": 44.553723611281114,
      "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": 952,
      "rating_method": "sequential_elo",
      "raw_elo": 1847.5349218158287,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 73.78797011506347,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 668
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1474,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4:483e8409583d40a0",
      "capped_draws": 40,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "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": 65.15382836806302,
      "contributing_entrants": null,
      "distinct_rated_opponents": 108,
      "draws": 227,
      "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": "2026-09-10T11:09:05Z",
      "losses": 321,
      "max_score": 91.89049593436994,
      "measured_at": null,
      "min_score": 26.86648580703239,
      "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": 1468,
      "rating_method": "sequential_elo",
      "raw_elo": 1764.7594151715166,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 63.01471156610657,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 920
    },
    {
      "admitted_plugins": 13,
      "attempted_matches": 626,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-5:a953aed661ace78d",
      "capped_draws": 1,
      "codegen_cost_usd": {
        "admitted_cell_count": 13,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 16
        },
        "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": 64.24813629810149,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 40,
      "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": "2026-08-05T04:44:12Z",
      "losses": 115,
      "max_score": 85.05036844756516,
      "measured_at": null,
      "min_score": 42.027298685176675,
      "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": 626,
      "rating_method": "sequential_elo",
      "raw_elo": 1771.0674028137453,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 60.99810969744108,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 14,
      "attempted_matches": 956,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-5:b56db7c91f30e821",
      "capped_draws": 15,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 16
        },
        "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": 62.639402761935784,
      "contributing_entrants": null,
      "distinct_rated_opponents": 68,
      "draws": 123,
      "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": "2026-08-05T05:35:16Z",
      "losses": 154,
      "max_score": 77.13223675647313,
      "measured_at": null,
      "min_score": 37.38045751660635,
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 956,
      "rating_method": "sequential_elo",
      "raw_elo": 1760.541512421418,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 60.582839053113815,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 679
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 978,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-fable-5:9411c67711dccbe8",
      "capped_draws": 60,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "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": 59.95385418281583,
      "contributing_entrants": null,
      "distinct_rated_opponents": 101,
      "draws": 169,
      "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": "2026-09-10T11:00:18Z",
      "losses": 289,
      "max_score": 85.88512253636422,
      "measured_at": null,
      "min_score": 37.59961008402652,
      "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": 972,
      "rating_method": "sequential_elo",
      "raw_elo": 1697.438766010291,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 59.95385418281583,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 8,
      "attempted_matches": 1008,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-3:2dbca3140c06e14c",
      "capped_draws": 61,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "evidence_basis": "Provider-reported",
        "max": 0.23469315999999998,
        "mean": 0.156944395,
        "median": 0.1664265,
        "min": 0.07192,
        "recorded_attempt_count": 10,
        "run_count": 8,
        "total": 1.2555551600000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 59.35550035157464,
      "contributing_entrants": null,
      "distinct_rated_opponents": 108,
      "draws": 176,
      "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": "2026-09-10T11:09:42Z",
      "losses": 321,
      "max_score": 95.8308881823799,
      "measured_at": null,
      "min_score": 24.766285822102056,
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1007,
      "rating_method": "sequential_elo",
      "raw_elo": 1687.8803688315882,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 59.35550035157464,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 14,
      "attempted_matches": 1216,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-5:2bf46853c4c2a3bc",
      "capped_draws": 124,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 16
        },
        "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": 4.570125
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 59.71965002282272,
      "contributing_entrants": null,
      "distinct_rated_opponents": 125,
      "draws": 248,
      "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": "2026-09-10T10:00:20Z",
      "losses": 219,
      "max_score": 81.06683069976471,
      "measured_at": null,
      "min_score": 36.957881306791684,
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1215,
      "rating_method": "sequential_elo",
      "raw_elo": 1722.6966437254782,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 57.75894702239247,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 748
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 425,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-5:a77a9da79f1450e0",
      "capped_draws": 31,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "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": 59.0535146259817,
      "contributing_entrants": null,
      "distinct_rated_opponents": 51,
      "draws": 80,
      "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": "2026-08-05T04:35:52Z",
      "losses": 92,
      "max_score": 82.05925729033785,
      "measured_at": null,
      "min_score": 17.140349376902293,
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 424,
      "rating_method": "sequential_elo",
      "raw_elo": 1724.6113224164167,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 57.11468204292295,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 252
    },
    {
      "admitted_plugins": 25,
      "attempted_matches": 3255,
      "canonical_public_row_identity": "publication-row.v1:mixed:stealth-ox-alpha:fe3b437dca2c4367",
      "capped_draws": 74,
      "codegen_cost_usd": {
        "admitted_cell_count": 25,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 31
        },
        "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": 56.86801757531599,
      "contributing_entrants": null,
      "distinct_rated_opponents": 113,
      "draws": 474,
      "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": "2026-09-10T11:09:55Z",
      "losses": 1116,
      "max_score": 63.32717677815119,
      "measured_at": null,
      "min_score": 47.83064684889641,
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3118,
      "rating_method": "sequential_elo",
      "raw_elo": 1647.1457974188295,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 56.86801757531599,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 131,
      "wins": 1528
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 446,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-8:95b343605f7f7184",
      "capped_draws": 13,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 9
        },
        "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": 58.213545390771856,
      "contributing_entrants": null,
      "distinct_rated_opponents": 53,
      "draws": 56,
      "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": "2026-08-05T03:23:19Z",
      "losses": 115,
      "max_score": 70.79490986212144,
      "measured_at": null,
      "min_score": 48.94611757043748,
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 446,
      "rating_method": "sequential_elo",
      "raw_elo": 1680.8148115126678,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 56.302290501137556,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 275
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 990,
      "canonical_public_row_identity": "publication-row.v1:mixed:x-ai-grok-4-6:bca3abc3bf41095f",
      "capped_draws": 34,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "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": 56.21231506536722,
      "contributing_entrants": null,
      "distinct_rated_opponents": 105,
      "draws": 196,
      "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": "2026-09-10T11:09:42Z",
      "losses": 307,
      "max_score": 74.21271794604775,
      "measured_at": null,
      "min_score": 18.364695347029407,
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 984,
      "rating_method": "sequential_elo",
      "raw_elo": 1688.994816387265,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 56.21231506536722,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 481
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1626,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-sol:92a27bf667504f91",
      "capped_draws": 84,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "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": 1.8325049999999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 56.18273720189021,
      "contributing_entrants": null,
      "distinct_rated_opponents": 108,
      "draws": 251,
      "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": "2026-09-10T11:07:47Z",
      "losses": 516,
      "max_score": 76.41507877251388,
      "measured_at": null,
      "min_score": 34.76336759556245,
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1625,
      "rating_method": "sequential_elo",
      "raw_elo": 1636.494237325968,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 56.18273720189021,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1034,
      "canonical_public_row_identity": "publication-row.v1:mixed:tencent-hy4-preview:2077a0aa15ce66b2",
      "capped_draws": 203,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "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": 54.78773402205262,
      "contributing_entrants": null,
      "distinct_rated_opponents": 109,
      "draws": 310,
      "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": "2026-09-10T11:05:01Z",
      "losses": 317,
      "max_score": 73.34304806796328,
      "measured_at": null,
      "min_score": 27.68709794444988,
      "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": 1028,
      "rating_method": "sequential_elo",
      "raw_elo": 1634.0101861421667,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 54.78773402205262,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 401
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1015,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:b4ca94f8b60a9e88",
      "capped_draws": 53,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 10
        },
        "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": 53.26667306538265,
      "contributing_entrants": null,
      "distinct_rated_opponents": 109,
      "draws": 267,
      "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": "2026-09-10T11:11:56Z",
      "losses": 312,
      "max_score": 85.08829766988379,
      "measured_at": null,
      "min_score": 29.297101237978474,
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1009,
      "rating_method": "sequential_elo",
      "raw_elo": 1646.398092070077,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 53.26667306538265,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 430
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1084,
      "canonical_public_row_identity": "publication-row.v1:mixed:x-ai-grok-4-6:d94ddefd8b9f53eb",
      "capped_draws": 99,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "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": 53.08560240806504,
      "contributing_entrants": null,
      "distinct_rated_opponents": 108,
      "draws": 242,
      "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": "2026-09-10T11:09:42Z",
      "losses": 371,
      "max_score": 82.4874985834472,
      "measured_at": null,
      "min_score": 23.843971005685763,
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1084,
      "rating_method": "sequential_elo",
      "raw_elo": 1631.618956826306,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 53.08560240806504,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 8,
      "attempted_matches": 992,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-8-flash:e50b23a03b02a00c",
      "capped_draws": 51,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 9
        },
        "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": 52.4147765736809,
      "contributing_entrants": null,
      "distinct_rated_opponents": 104,
      "draws": 149,
      "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": "2026-09-10T11:00:26Z",
      "losses": 421,
      "max_score": 79.59975068636147,
      "measured_at": null,
      "min_score": 35.81130147891559,
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 991,
      "rating_method": "sequential_elo",
      "raw_elo": 1627.3108629141504,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 52.4147765736809,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 421
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1027,
      "canonical_public_row_identity": "publication-row.v1:mixed:meta-muse-spark-1-3:111be2eb4c7d6522",
      "capped_draws": 11,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "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": 51.9876898864305,
      "contributing_entrants": null,
      "distinct_rated_opponents": 106,
      "draws": 146,
      "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": "2026-09-10T11:12:08Z",
      "losses": 432,
      "max_score": 76.70363100762701,
      "measured_at": null,
      "min_score": 31.93233314474059,
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1019,
      "rating_method": "sequential_elo",
      "raw_elo": 1627.6642228917171,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 51.9876898864305,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 441
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 3029,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-6-flash:b4583ef7c04d45cd",
      "capped_draws": 390,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 53
        },
        "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": 55.68219526351658,
      "contributing_entrants": null,
      "distinct_rated_opponents": 127,
      "draws": 566,
      "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": "2026-09-10T11:10:23Z",
      "losses": 885,
      "max_score": 85.6020891745296,
      "measured_at": null,
      "min_score": 38.850120833000595,
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3023,
      "rating_method": "sequential_elo",
      "raw_elo": 1640.8133672735662,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 51.818121477700444,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 1572
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2144,
      "canonical_public_row_identity": "publication-row.v1:mixed:x-ai-grok-4-5:5e133fd8ec34ed0c",
      "capped_draws": 82,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "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": 51.6937015030495,
      "contributing_entrants": null,
      "distinct_rated_opponents": 126,
      "draws": 407,
      "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": "2026-09-10T10:53:15Z",
      "losses": 599,
      "max_score": 81.02581011754175,
      "measured_at": null,
      "min_score": 14.194010354631436,
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2144,
      "rating_method": "sequential_elo",
      "raw_elo": 1628.8388345128037,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 51.6937015030495,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1138
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 958,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-3-flash:1540ade2fda6b881",
      "capped_draws": 113,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "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": 49.69482600982666,
      "contributing_entrants": null,
      "distinct_rated_opponents": 110,
      "draws": 232,
      "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": "2026-09-10T11:06:10Z",
      "losses": 348,
      "max_score": 71.64471752845151,
      "measured_at": null,
      "min_score": 17.540748548543018,
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 958,
      "rating_method": "sequential_elo",
      "raw_elo": 1558.9694711820664,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 49.69482600982666,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 954,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-fable-5:1f4ca1763387a608",
      "capped_draws": 16,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "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": 49.646949204317174,
      "contributing_entrants": null,
      "distinct_rated_opponents": 108,
      "draws": 197,
      "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": "2026-09-10T11:07:59Z",
      "losses": 344,
      "max_score": 77.10732678766597,
      "measured_at": null,
      "min_score": 10.636544202241724,
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 954,
      "rating_method": "sequential_elo",
      "raw_elo": 1620.6537941577335,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 49.646949204317174,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 413
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1022,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-3-flash:6bc93e3f26e0f0e5",
      "capped_draws": 110,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "evidence_basis": "Provider-reported",
        "max": 0.01518705,
        "mean": 0.00578608125,
        "median": 0.0045066875,
        "min": 0.0032555,
        "recorded_attempt_count": 8,
        "run_count": 8,
        "total": 0.04628865000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 48.74706488440559,
      "contributing_entrants": null,
      "distinct_rated_opponents": 109,
      "draws": 292,
      "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": "2026-09-10T11:06:10Z",
      "losses": 336,
      "max_score": 75.69077551550029,
      "measured_at": null,
      "min_score": 13.629201190774216,
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1015,
      "rating_method": "sequential_elo",
      "raw_elo": 1594.6691703367667,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 48.74706488440559,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 387
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1022,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-5-flash:188028ef432c73f8",
      "capped_draws": 58,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 11
        },
        "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": 48.242638257789736,
      "contributing_entrants": null,
      "distinct_rated_opponents": 109,
      "draws": 230,
      "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": "2026-09-10T10:48:35Z",
      "losses": 378,
      "max_score": 82.02311872112153,
      "measured_at": null,
      "min_score": 19.436408028603687,
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1022,
      "rating_method": "sequential_elo",
      "raw_elo": 1603.15565731743,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 48.242638257789736,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 414
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 656,
      "canonical_public_row_identity": "publication-row.v1:mixed:x-ai-grok-4-5:a7aa1873ad17dbcc",
      "capped_draws": 9,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "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": 47.885604863809434,
      "contributing_entrants": null,
      "distinct_rated_opponents": 59,
      "draws": 146,
      "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": "2026-08-05T05:42:30Z",
      "losses": 173,
      "max_score": 75.36004018487888,
      "measured_at": null,
      "min_score": 15.084858110615464,
      "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": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 654,
      "rating_method": "sequential_elo",
      "raw_elo": 1608.1090208290418,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 47.885604863809434,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 335
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1051,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-flash:98dfb2fac355b676",
      "capped_draws": 156,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "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": 47.54012688882566,
      "contributing_entrants": null,
      "distinct_rated_opponents": 109,
      "draws": 346,
      "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": "2026-09-10T11:11:42Z",
      "losses": 337,
      "max_score": 72.14023042347958,
      "measured_at": null,
      "min_score": 19.25382084260791,
      "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": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1050,
      "rating_method": "sequential_elo",
      "raw_elo": 1597.9463423744303,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 47.54012688882566,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1052,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-8-flash:6b8b02f1f727feff",
      "capped_draws": 133,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "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": 0.5746151281850015
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 47.189592263291324,
      "contributing_entrants": null,
      "distinct_rated_opponents": 110,
      "draws": 335,
      "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": "2026-09-10T11:10:07Z",
      "losses": 322,
      "max_score": 75.82334053498934,
      "measured_at": null,
      "min_score": 7.902824182042486,
      "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": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1046,
      "rating_method": "sequential_elo",
      "raw_elo": 1590.1142917632478,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 47.189592263291324,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 389
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 767,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-27b:739c4d774075dc83",
      "capped_draws": 64,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "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": 50.590074067871484,
      "contributing_entrants": null,
      "distinct_rated_opponents": 109,
      "draws": 107,
      "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": "2026-09-10T11:11:13Z",
      "losses": 316,
      "max_score": 74.97439218948013,
      "measured_at": null,
      "min_score": 29.853834414688254,
      "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": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 767,
      "rating_method": "sequential_elo",
      "raw_elo": 1558.5319824190376,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 47.079368749896325,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 344
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 960,
      "canonical_public_row_identity": "publication-row.v1:mixed:tencent-hy4-preview:014a9ceb67d5b786",
      "capped_draws": 13,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "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": 48.51069202035984,
      "contributing_entrants": null,
      "distinct_rated_opponents": 110,
      "draws": 178,
      "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": "2026-09-10T11:06:19Z",
      "losses": 362,
      "max_score": 86.09465836643398,
      "measured_at": null,
      "min_score": 9.230754142229273,
      "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": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 960,
      "rating_method": "sequential_elo",
      "raw_elo": 1581.2308295981145,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 46.917999173685125,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 420
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1762,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4:672219b99ff5a80c",
      "capped_draws": 186,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "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": 46.19996042414856,
      "contributing_entrants": null,
      "distinct_rated_opponents": 114,
      "draws": 598,
      "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": "2026-09-10T11:06:20Z",
      "losses": 442,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 9.48709633237125,
      "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": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1756,
      "rating_method": "sequential_elo",
      "raw_elo": 1598.3142606272136,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 46.19996042414856,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 716
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 580,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-5:1a25631bf54a6363",
      "capped_draws": 91,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "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": 45.65211067782296,
      "contributing_entrants": null,
      "distinct_rated_opponents": 60,
      "draws": 196,
      "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": "2026-08-05T04:43:10Z",
      "losses": 155,
      "max_score": 66.31252434317867,
      "measured_at": null,
      "min_score": 23.27457919744084,
      "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": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 580,
      "rating_method": "sequential_elo",
      "raw_elo": 1579.7486408374518,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 45.65211067782296,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 229
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2356,
      "canonical_public_row_identity": "publication-row.v1:mixed:moonshotai-kimi-k3:f0bfe8c58b2cc988",
      "capped_draws": 203,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "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": 45.45362312867519,
      "contributing_entrants": null,
      "distinct_rated_opponents": 134,
      "draws": 654,
      "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": "2026-09-10T10:38:53Z",
      "losses": 769,
      "max_score": 89.21089685186311,
      "measured_at": null,
      "min_score": 11.367330732070096,
      "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": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2356,
      "rating_method": "sequential_elo",
      "raw_elo": 1553.5581213722062,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 45.45362312867519,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 933
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1686,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-luna:e05ef4cc93414f96",
      "capped_draws": 172,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "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": 45.30312374197206,
      "contributing_entrants": null,
      "distinct_rated_opponents": 114,
      "draws": 576,
      "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": "2026-09-10T11:08:37Z",
      "losses": 458,
      "max_score": 79.12179151899733,
      "measured_at": null,
      "min_score": 10.237515749847217,
      "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": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1682,
      "rating_method": "sequential_elo",
      "raw_elo": 1583.0255194022957,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 45.30312374197206,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 648
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 2925,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-6-flash:13a24e3021af753a",
      "capped_draws": 244,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 44
        },
        "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": 46.76079180174214,
      "contributing_entrants": null,
      "distinct_rated_opponents": 168,
      "draws": 730,
      "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": "2026-09-10T11:10:23Z",
      "losses": 807,
      "max_score": 77.74963744928857,
      "measured_at": null,
      "min_score": 6.451833831046862,
      "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": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2923,
      "rating_method": "sequential_elo",
      "raw_elo": 1600.6651747084215,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 45.225551311331834,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1386
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1096,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-fable-5:346aadd5d76b812b",
      "capped_draws": 30,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "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": 2.3088499999999996
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 44.77941641806791,
      "contributing_entrants": null,
      "distinct_rated_opponents": 110,
      "draws": 320,
      "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": "2026-09-10T11:07:47Z",
      "losses": 376,
      "max_score": 70.16961646402447,
      "measured_at": null,
      "min_score": 6.646568053595592,
      "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": 40,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1095,
      "rating_method": "sequential_elo",
      "raw_elo": 1575.203509271904,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 44.77941641806791,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 399
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1819,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-sol:e7389fafab42de55",
      "capped_draws": 36,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "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": 44.64382299490942,
      "contributing_entrants": null,
      "distinct_rated_opponents": 113,
      "draws": 416,
      "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": "2026-09-10T11:12:01Z",
      "losses": 581,
      "max_score": 71.00149057401816,
      "measured_at": null,
      "min_score": 13.272080636024716,
      "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": 41,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1818,
      "rating_method": "sequential_elo",
      "raw_elo": 1554.1661383056335,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 44.64382299490942,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 821
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1658,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-sonnet-5:ec6362fd3d2a0220",
      "capped_draws": 32,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "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": 43.54754891745874,
      "contributing_entrants": null,
      "distinct_rated_opponents": 112,
      "draws": 376,
      "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": "2026-09-10T10:25:59Z",
      "losses": 619,
      "max_score": 74.33339438299416,
      "measured_at": null,
      "min_score": 7.484704864315055,
      "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": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1657,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.1533988456465,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 43.54754891745874,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 662
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 496,
      "canonical_public_row_identity": "publication-row.v1:mixed:o3:f70fd8105d3dfec2",
      "capped_draws": 68,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "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": 0.39097600000000005
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 46.63103950637711,
      "contributing_entrants": null,
      "distinct_rated_opponents": 60,
      "draws": 127,
      "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": "2026-08-05T05:17:46Z",
      "losses": 152,
      "max_score": 64.65603985716929,
      "measured_at": null,
      "min_score": 22.72518278425092,
      "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": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 496,
      "rating_method": "sequential_elo",
      "raw_elo": 1555.7512446698092,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 43.39507194961651,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 217
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1050,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-5-flash:79befaaad7974375",
      "capped_draws": 80,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 10
        },
        "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": 1.5865090123478316
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.70271893536102,
      "contributing_entrants": null,
      "distinct_rated_opponents": 110,
      "draws": 323,
      "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": "2026-09-10T11:09:43Z",
      "losses": 407,
      "max_score": 69.56944867447089,
      "measured_at": null,
      "min_score": 12.10378519941586,
      "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": 44,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1049,
      "rating_method": "sequential_elo",
      "raw_elo": 1544.1927472622533,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 42.70271893536102,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 319
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 572,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-8:8ccf8977401d94db",
      "capped_draws": 82,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "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": 42.12697825585987,
      "contributing_entrants": null,
      "distinct_rated_opponents": 62,
      "draws": 228,
      "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": "2026-08-05T03:49:27Z",
      "losses": 134,
      "max_score": 70.46838917607434,
      "measured_at": null,
      "min_score": 10.886852859373011,
      "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": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 572,
      "rating_method": "sequential_elo",
      "raw_elo": 1555.5846759385058,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 42.12697825585987,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 210
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 621,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4-mini:e296afd987da0af3",
      "capped_draws": 40,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "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": 41.94270122706257,
      "contributing_entrants": null,
      "distinct_rated_opponents": 58,
      "draws": 182,
      "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": "2026-08-05T06:55:18Z",
      "losses": 182,
      "max_score": 56.015466910410275,
      "measured_at": null,
      "min_score": 15.520290105513986,
      "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": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 619,
      "rating_method": "sequential_elo",
      "raw_elo": 1533.158871524542,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 41.94270122706257,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 255
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 470,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-8:c5e685ce6c400bea",
      "capped_draws": 17,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "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": 43.264323114773916,
      "contributing_entrants": null,
      "distinct_rated_opponents": 61,
      "draws": 130,
      "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": "2026-08-05T03:47:33Z",
      "losses": 134,
      "max_score": 60.46952997771049,
      "measured_at": null,
      "min_score": 15.08783877564788,
      "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": 47,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 470,
      "rating_method": "sequential_elo",
      "raw_elo": 1554.5581239066864,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 41.84387794956778,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 206
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 574,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-5:959db58a0f4d59b9",
      "capped_draws": 74,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "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": 41.44919981470518,
      "contributing_entrants": null,
      "distinct_rated_opponents": 61,
      "draws": 198,
      "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": "2026-08-05T05:02:30Z",
      "losses": 173,
      "max_score": 57.33994820345935,
      "measured_at": null,
      "min_score": 16.904129430402378,
      "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": 48,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 574,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.7089756027547,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 41.44919981470518,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 203
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1074,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:d0b5b92265541548",
      "capped_draws": 107,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "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": 41.37071157031049,
      "contributing_entrants": null,
      "distinct_rated_opponents": 111,
      "draws": 333,
      "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": "2026-09-10T11:09:39Z",
      "losses": 334,
      "max_score": 74.8155896456324,
      "measured_at": null,
      "min_score": 9.963827021369582,
      "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": 49,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1074,
      "rating_method": "sequential_elo",
      "raw_elo": 1530.5882675031414,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 41.37071157031049,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 407
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 486,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-7-plus:e4e482b5c34e690f",
      "capped_draws": 91,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 16
        },
        "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": 0.43500896
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 44.42570551005691,
      "contributing_entrants": null,
      "distinct_rated_opponents": 61,
      "draws": 150,
      "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": "2026-08-05T03:48:47Z",
      "losses": 158,
      "max_score": 70.99957787144118,
      "measured_at": null,
      "min_score": 15.204208993992154,
      "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": 50,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 486,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.324560555531,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 41.34277741669788,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 178
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1541,
      "canonical_public_row_identity": "publication-row.v1:mixed:meta-muse-spark-1-2:0ef600658249027b",
      "capped_draws": 63,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "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": 0.37616799999999995
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.735701184984805,
      "contributing_entrants": null,
      "distinct_rated_opponents": 111,
      "draws": 379,
      "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": "2026-09-10T10:59:40Z",
      "losses": 549,
      "max_score": 64.21230002498487,
      "measured_at": null,
      "min_score": 13.992136416293384,
      "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": 51,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1540,
      "rating_method": "sequential_elo",
      "raw_elo": 1558.3591357051268,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 41.33261162389615,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 612
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1018,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-pro:c37d073d6b142a09",
      "capped_draws": 13,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "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": 40.91602273478811,
      "contributing_entrants": null,
      "distinct_rated_opponents": 111,
      "draws": 237,
      "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": "2026-09-10T10:50:08Z",
      "losses": 354,
      "max_score": 65.49910556920233,
      "measured_at": null,
      "min_score": 8.46888583743832,
      "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": 52,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1018,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.129488075388,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 40.91602273478811,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 484,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5:3bb27dbc092c7ff2",
      "capped_draws": 61,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "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": 42.256499987447725,
      "contributing_entrants": null,
      "distinct_rated_opponents": 56,
      "draws": 138,
      "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": "2026-08-05T05:19:06Z",
      "losses": 160,
      "max_score": 64.90905738242017,
      "measured_at": null,
      "min_score": 25.31798930091367,
      "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": 53,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 484,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.3373874396289,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 40.869143459380226,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 186
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1066,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-8-flash:83795e08736dcbd6",
      "capped_draws": 71,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "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": 40.688636894322386,
      "contributing_entrants": null,
      "distinct_rated_opponents": 110,
      "draws": 269,
      "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": "2026-09-10T11:11:52Z",
      "losses": 427,
      "max_score": 69.17178746172216,
      "measured_at": null,
      "min_score": 6.964348588339904,
      "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": 1065,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.5215652120276,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 40.688636894322386,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 369
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 515,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5:16f7def69ce10ccd",
      "capped_draws": 57,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "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": 2.2561125
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.5842067414882,
      "contributing_entrants": null,
      "distinct_rated_opponents": 63,
      "draws": 165,
      "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": "2026-08-05T05:05:23Z",
      "losses": 176,
      "max_score": 65.51337979360243,
      "measured_at": null,
      "min_score": 12.515897799774466,
      "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": 55,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 514,
      "rating_method": "sequential_elo",
      "raw_elo": 1538.8348441013682,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 40.5842067414882,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 173
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1136,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-max:644816d2bc8a5f5c",
      "capped_draws": 92,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "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": 0.8354799999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.97699964131566,
      "contributing_entrants": null,
      "distinct_rated_opponents": 112,
      "draws": 371,
      "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": "2026-09-10T11:05:43Z",
      "losses": 410,
      "max_score": 61.62273404542139,
      "measured_at": null,
      "min_score": 12.997248213621113,
      "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": 56,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1135,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.3432547298382,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 39.97699964131566,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 354
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1121,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-max:7b21229bd01e0b5e",
      "capped_draws": 131,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "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": 42.05605079183701,
      "contributing_entrants": null,
      "distinct_rated_opponents": 110,
      "draws": 305,
      "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": "2026-09-10T11:11:37Z",
      "losses": 420,
      "max_score": 73.66211615758745,
      "measured_at": null,
      "min_score": 22.390163615050678,
      "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": 57,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1121,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.948054319958,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 39.77415714419122,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 396
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1100,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-terra:bd3aacb7be18fc49",
      "capped_draws": 98,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "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": 39.668834509119144,
      "contributing_entrants": null,
      "distinct_rated_opponents": 114,
      "draws": 326,
      "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": "2026-09-10T10:37:07Z",
      "losses": 380,
      "max_score": 69.43940999034174,
      "measured_at": null,
      "min_score": 17.367291620527613,
      "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": 58,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1100,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.3727889411705,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 39.668834509119144,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 394
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 566,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-7-max:fa240f0afd3eda59",
      "capped_draws": 83,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "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": 40.38266609921668,
      "contributing_entrants": null,
      "distinct_rated_opponents": 58,
      "draws": 206,
      "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": "2026-08-05T05:35:11Z",
      "losses": 170,
      "max_score": 71.61968219996771,
      "measured_at": null,
      "min_score": 12.895585775886488,
      "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": 59,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 566,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.1180674247914,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 39.05683089161168,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 190
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1065,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-pro:42034002bcfc5f74",
      "capped_draws": 121,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "evidence_basis": "Provider-reported",
        "max": 0.176790095,
        "mean": 0.114196574281125,
        "median": 0.09418628700000001,
        "min": 0.06074422244,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.913572594249
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.9734452809923,
      "contributing_entrants": null,
      "distinct_rated_opponents": 112,
      "draws": 348,
      "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": "2026-09-10T11:11:38Z",
      "losses": 388,
      "max_score": 70.6332524935784,
      "measured_at": null,
      "min_score": 10.858956125600434,
      "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": 60,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1065,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.8987740716207,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 38.9734452809923,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 329
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1036,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-2:4571486d5f3c5826",
      "capped_draws": 214,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "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": 38.789743684206364,
      "contributing_entrants": null,
      "distinct_rated_opponents": 113,
      "draws": 410,
      "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": "2026-09-10T11:10:18Z",
      "losses": 357,
      "max_score": 78.16337250474885,
      "measured_at": null,
      "min_score": 16.982534527025862,
      "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": 61,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1036,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.137792714452,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 38.789743684206364,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 269
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 408,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-2:f14efcbac580ffaa",
      "capped_draws": 59,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 16
        },
        "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": 38.49286082845098,
      "contributing_entrants": null,
      "distinct_rated_opponents": 56,
      "draws": 163,
      "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": "2026-07-31T03:34:47Z",
      "losses": 110,
      "max_score": 66.11834084034295,
      "measured_at": null,
      "min_score": 11.957291644537442,
      "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": 62,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 408,
      "rating_method": "sequential_elo",
      "raw_elo": 1521.0242599747953,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 38.49286082845098,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 135
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 492,
      "canonical_public_row_identity": "publication-row.v1:mixed:moonshotai-kimi-k2-7-code:0eac35852db14de0",
      "capped_draws": 10,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "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": 1.283003154
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 41.10005622496815,
      "contributing_entrants": null,
      "distinct_rated_opponents": 59,
      "draws": 143,
      "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": "2026-08-05T05:26:41Z",
      "losses": 159,
      "max_score": 55.31987902290327,
      "measured_at": null,
      "min_score": 15.971215353629413,
      "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": 63,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 492,
      "rating_method": "sequential_elo",
      "raw_elo": 1543.1361607461313,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 38.247912032324855,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 190
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1022,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-3-flash:22cd36959459fbdd",
      "capped_draws": 173,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "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": 37.903624046046815,
      "contributing_entrants": null,
      "distinct_rated_opponents": 111,
      "draws": 368,
      "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": "2026-09-10T11:08:42Z",
      "losses": 336,
      "max_score": 65.32971726850512,
      "measured_at": null,
      "min_score": 8.088342646823264,
      "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": 64,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1022,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.56890944493,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 37.903624046046815,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 318
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 472,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-7-max:a92ef5f3c3f212e3",
      "capped_draws": 82,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "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": 39.16034768625658,
      "contributing_entrants": null,
      "distinct_rated_opponents": 59,
      "draws": 161,
      "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": "2026-08-05T05:33:39Z",
      "losses": 162,
      "max_score": 59.55002702144701,
      "measured_at": null,
      "min_score": 17.63292970387716,
      "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": 65,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 472,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.1419776261966,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 37.87464337993543,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 149
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2230,
      "canonical_public_row_identity": "publication-row.v1:mixed:moonshotai-kimi-k3:6a00f2f5a49a8584",
      "capped_draws": 294,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 16
        },
        "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": 37.79492618629287,
      "contributing_entrants": null,
      "distinct_rated_opponents": 138,
      "draws": 758,
      "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": "2026-09-10T10:40:09Z",
      "losses": 792,
      "max_score": 60.02690569508898,
      "measured_at": null,
      "min_score": 6.485222218768579,
      "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": 66,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2220,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.9366584163504,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 37.79492618629287,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 16,
      "attempted_matches": 832,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-2:5ea14bc9644b6a2b",
      "capped_draws": 67,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 24
        },
        "evidence_basis": "Provider-reported",
        "max": 0.047757869999999994,
        "mean": 0.022448211274999998,
        "median": 0.017169796,
        "min": 0.0106770175,
        "recorded_attempt_count": 24,
        "run_count": 16,
        "total": 0.35917138039999996
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 37.78183275569055,
      "contributing_entrants": null,
      "distinct_rated_opponents": 60,
      "draws": 273,
      "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": "2026-07-31T20:23:06Z",
      "losses": 281,
      "max_score": 57.999842290797865,
      "measured_at": null,
      "min_score": 12.099457750098598,
      "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": 67,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 832,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.3396038818432,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 37.78183275569055,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 278
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1058,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-terra:ac05ef4b9a51340d",
      "capped_draws": 42,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "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": 37.628448345284106,
      "contributing_entrants": null,
      "distinct_rated_opponents": 112,
      "draws": 301,
      "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": "2026-09-10T10:58:30Z",
      "losses": 443,
      "max_score": 61.83347349707339,
      "measured_at": null,
      "min_score": 10.442043596500689,
      "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": 68,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1058,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.9798187871947,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 37.628448345284106,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 314
    },
    {
      "admitted_plugins": 19,
      "attempted_matches": 5128,
      "canonical_public_row_identity": "publication-row.v1:mixed:o3:1084c60ee563e860",
      "capped_draws": 472,
      "codegen_cost_usd": {
        "admitted_cell_count": 19,
        "cell_count": 8,
        "cost_basis_counts": {
          "estimated": 32,
          "local_standard_estimate": 8
        },
        "evidence_basis": "Combined: Recorded attempt + Standard list-price estimate",
        "failed_cell_count": 13,
        "max": 0.1097735,
        "mean": 0.091486,
        "median": 0.08840575,
        "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": 42.65797926498379,
      "contributing_entrants": null,
      "distinct_rated_opponents": 123,
      "draws": 590,
      "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": "2026-09-10T11:10:18Z",
      "losses": 2264,
      "max_score": 49.93788221593318,
      "measured_at": null,
      "min_score": 31.45724153790146,
      "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": 69,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 5128,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.7485661098071,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 37.44563368460245,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 2274
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2227,
      "canonical_public_row_identity": "publication-row.v1:mixed:x-ai-grok-4-5:365663c1de2ba20d",
      "capped_draws": 200,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "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": 37.20786073928545,
      "contributing_entrants": null,
      "distinct_rated_opponents": 134,
      "draws": 696,
      "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": "2026-09-10T11:11:37Z",
      "losses": 759,
      "max_score": 69.67529740665044,
      "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": 70,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2227,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.3095894734206,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 37.20786073928545,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 772
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1728,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4:cea8a68bd875deb9",
      "capped_draws": 176,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "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": 37.161284828496534,
      "contributing_entrants": null,
      "distinct_rated_opponents": 113,
      "draws": 582,
      "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": "2026-09-10T11:11:29Z",
      "losses": 616,
      "max_score": 64.11149296941215,
      "measured_at": null,
      "min_score": 8.247425935777672,
      "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": 71,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1728,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.3571984020155,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 37.161284828496534,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 530
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 884,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4-nano:4caf0453cfb54e62",
      "capped_draws": 63,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 25
        },
        "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": 0.39544915
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 39.62662596514345,
      "contributing_entrants": null,
      "distinct_rated_opponents": 66,
      "draws": 172,
      "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": "2026-08-05T06:55:07Z",
      "losses": 344,
      "max_score": 60.07944202124918,
      "measured_at": null,
      "min_score": 12.950917619586493,
      "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": 72,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 882,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.6010568667577,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 36.87673067298392,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 366
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 572,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-4-1:731bd482a4919a05",
      "capped_draws": 71,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 11
        },
        "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": 0.4575640000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 35.80056693008479,
      "contributing_entrants": null,
      "distinct_rated_opponents": 68,
      "draws": 196,
      "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": "2026-08-05T05:41:31Z",
      "losses": 198,
      "max_score": 55.88308492443146,
      "measured_at": null,
      "min_score": 11.682283349084813,
      "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": 73,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 571,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.7983515817293,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 35.80056693008479,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 177
    },
    {
      "admitted_plugins": 26,
      "attempted_matches": 3609,
      "canonical_public_row_identity": "publication-row.v1:mixed:stealth-ox-alpha:6719f8157bcde29f",
      "capped_draws": 225,
      "codegen_cost_usd": {
        "admitted_cell_count": 26,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 39
        },
        "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": 36.85392471914304,
      "contributing_entrants": null,
      "distinct_rated_opponents": 114,
      "draws": 847,
      "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": "2026-09-10T11:12:08Z",
      "losses": 1488,
      "max_score": 48.22093354536652,
      "measured_at": null,
      "min_score": 16.948694007756043,
      "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": 74,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3600,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.2697748344724,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 35.55877308298843,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1265
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1002,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:f9ec308f9bb8850b",
      "capped_draws": 71,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 9
        },
        "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": 35.210841176918336,
      "contributing_entrants": null,
      "distinct_rated_opponents": 113,
      "draws": 281,
      "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": "2026-09-10T10:39:03Z",
      "losses": 365,
      "max_score": 64.6317689865653,
      "measured_at": null,
      "min_score": 11.392747323534184,
      "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": 75,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1001,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.6088649070266,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 35.210841176918336,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 355
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 620,
      "canonical_public_row_identity": "publication-row.v1:mixed:x-ai-grok-build-0-1:55f4f20890a40d69",
      "capped_draws": 84,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "evidence_basis": "Provider-reported",
        "max": 0.07439860000000001,
        "mean": 0.060660574999999994,
        "median": 0.0565846,
        "min": 0.0485456,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 0.4852846
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 35.20852304594772,
      "contributing_entrants": null,
      "distinct_rated_opponents": 63,
      "draws": 230,
      "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": "2026-08-05T05:34:43Z",
      "losses": 205,
      "max_score": 65.57660382357807,
      "measured_at": null,
      "min_score": 12.336802440575292,
      "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": 76,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 620,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.342191111961,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 35.20852304594772,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 185
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1002,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-3:9e30a36ab00bd740",
      "capped_draws": 114,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "evidence_basis": "Provider-reported",
        "max": 0.1610404,
        "mean": 0.053977109999999995,
        "median": 0.0318207,
        "min": 0.0217974,
        "recorded_attempt_count": 8,
        "run_count": 8,
        "total": 0.43181687999999996
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 35.13669356616318,
      "contributing_entrants": null,
      "distinct_rated_opponents": 112,
      "draws": 348,
      "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": "2026-09-10T11:09:46Z",
      "losses": 388,
      "max_score": 61.34368150573174,
      "measured_at": null,
      "min_score": 10.263403044539475,
      "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": 77,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1000,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.325274967785,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 35.13669356616318,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 264
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1136,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-flash:14b865d3f352c468",
      "capped_draws": 62,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "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": 35.08480938106314,
      "contributing_entrants": null,
      "distinct_rated_opponents": 113,
      "draws": 362,
      "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": "2026-09-10T11:08:34Z",
      "losses": 411,
      "max_score": 50.555220904982725,
      "measured_at": null,
      "min_score": 9.262937256635835,
      "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": 78,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1134,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.5489353985258,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 35.08480938106314,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1154,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:d3192451477fbf98",
      "capped_draws": 181,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "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": 34.223607878349945,
      "contributing_entrants": null,
      "distinct_rated_opponents": 111,
      "draws": 348,
      "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": "2026-09-10T11:10:07Z",
      "losses": 435,
      "max_score": 71.89246349927906,
      "measured_at": null,
      "min_score": 0.0,
      "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": 1148,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.9387678678388,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 34.223607878349945,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 365
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 436,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5:35035a0b78826dbc",
      "capped_draws": 63,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "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": 0.0306854728
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 36.64541850781422,
      "contributing_entrants": null,
      "distinct_rated_opponents": 59,
      "draws": 92,
      "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": "2026-08-05T05:41:45Z",
      "losses": 199,
      "max_score": 60.89199866384945,
      "measured_at": null,
      "min_score": 20.768995001529465,
      "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": 80,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 434,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.362058909666,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 34.10240452720193,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 143
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 454,
      "canonical_public_row_identity": "publication-row.v1:mixed:minimax-minimax-m3:6639861dd7b73e51",
      "capped_draws": 23,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "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": 0.20304798
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 36.383144914207264,
      "contributing_entrants": null,
      "distinct_rated_opponents": 61,
      "draws": 101,
      "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": "2026-08-05T04:33:21Z",
      "losses": 180,
      "max_score": 46.440218311437484,
      "measured_at": null,
      "min_score": 12.190471042456242,
      "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": 81,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 454,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.4791809138806,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 33.85833144657712,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 173
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1733,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-sonnet-5:73f1b29a5c45562d",
      "capped_draws": 228,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "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": 33.75922437630374,
      "contributing_entrants": null,
      "distinct_rated_opponents": 114,
      "draws": 573,
      "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": "2026-09-10T11:08:22Z",
      "losses": 573,
      "max_score": 50.753970891959106,
      "measured_at": null,
      "min_score": 13.459089329828975,
      "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": 82,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1733,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.7515433483236,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 33.75922437630374,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 587
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 534,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-5:53d4c02c8a9496db",
      "capped_draws": 145,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "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": 34.83562498827739,
      "contributing_entrants": null,
      "distinct_rated_opponents": 59,
      "draws": 275,
      "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": "2026-08-05T05:23:57Z",
      "losses": 149,
      "max_score": 49.787345255628644,
      "measured_at": null,
      "min_score": 13.936024036303673,
      "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": 83,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 534,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.652701429713,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 33.69190906880573,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1090,
      "canonical_public_row_identity": "publication-row.v1:mixed:tencent-hy4-preview:b8e7119f660161ad",
      "capped_draws": 150,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "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": 33.54804237444562,
      "contributing_entrants": null,
      "distinct_rated_opponents": 110,
      "draws": 404,
      "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": "2026-09-10T11:11:38Z",
      "losses": 341,
      "max_score": 48.348251895031375,
      "measured_at": null,
      "min_score": 7.401997425923536,
      "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": 84,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1090,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.3365216218722,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 33.54804237444562,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 345
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1120,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-max:a791831295f0ee80",
      "capped_draws": 143,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "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": 33.52240330497203,
      "contributing_entrants": null,
      "distinct_rated_opponents": 113,
      "draws": 423,
      "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": "2026-09-10T10:49:44Z",
      "losses": 375,
      "max_score": 88.76990902930297,
      "measured_at": null,
      "min_score": 6.07109411954341,
      "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": 85,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1120,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.2548859983672,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 33.52240330497203,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 8,
      "attempted_matches": 1728,
      "canonical_public_row_identity": "publication-row.v1:mixed:meta-muse-spark-1-2:539f99e7c4c4b6ea",
      "capped_draws": 107,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "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": 33.482296955476336,
      "contributing_entrants": null,
      "distinct_rated_opponents": 114,
      "draws": 416,
      "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": "2026-09-10T11:08:49Z",
      "losses": 772,
      "max_score": 53.37102488938938,
      "measured_at": null,
      "min_score": 3.906687867060584,
      "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": 86,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1728,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.0124587833386,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 33.482296955476336,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 540
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": 674,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5:235a446f3a9f9cd3",
      "capped_draws": 79,
      "codegen_cost_usd": {
        "admitted_cell_count": 11,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 25
        },
        "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": 0.038219743
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 36.69531546297876,
      "contributing_entrants": null,
      "distinct_rated_opponents": 63,
      "draws": 205,
      "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": "2026-07-31T20:23:03Z",
      "losses": 231,
      "max_score": 52.34975966070658,
      "measured_at": null,
      "min_score": 10.940010823479835,
      "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": 87,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 674,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.2962961158335,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 33.414025617082295,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 238
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 1219,
      "canonical_public_row_identity": "publication-row.v1:mixed:poolside-laguna-s-2-1:533b6103a5973424",
      "capped_draws": 203,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 33
        },
        "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": 34.67716153953121,
      "contributing_entrants": null,
      "distinct_rated_opponents": 137,
      "draws": 429,
      "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": "2026-09-10T08:23:32Z",
      "losses": 408,
      "max_score": 54.10090278289114,
      "measured_at": null,
      "min_score": 9.449979970240136,
      "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": 88,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1211,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.3951550877723,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 33.36620733645767,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 374
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": 4003,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-5-flash-lite:55634764b9427e4e",
      "capped_draws": 590,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 34
        },
        "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": 33.8042060754052,
      "contributing_entrants": null,
      "distinct_rated_opponents": 135,
      "draws": 1362,
      "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": "2026-09-10T11:12:00Z",
      "losses": 1532,
      "max_score": 65.89914757897805,
      "measured_at": null,
      "min_score": 9.623986038775216,
      "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": 89,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3997,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.6909229985479,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 33.26316420086277,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1103
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1134,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:78fb6a9e00356b09",
      "capped_draws": 166,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "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": 33.21730372205993,
      "contributing_entrants": null,
      "distinct_rated_opponents": 112,
      "draws": 428,
      "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": "2026-09-10T10:48:35Z",
      "losses": 375,
      "max_score": 50.52600493863421,
      "measured_at": null,
      "min_score": 8.285036037313507,
      "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": 90,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1131,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.2517713468794,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 33.21730372205993,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 328
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1725,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-luna:29e28a5adce9180a",
      "capped_draws": 196,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "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": 0.05054445
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 33.21050354010995,
      "contributing_entrants": null,
      "distinct_rated_opponents": 113,
      "draws": 590,
      "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": "2026-09-10T11:05:04Z",
      "losses": 614,
      "max_score": 51.75536719315471,
      "measured_at": null,
      "min_score": 12.208818148161988,
      "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": 91,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1724,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.187551087428,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 33.21050354010995,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 520
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1698,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-sonnet-5:a86621e2793b5dec",
      "capped_draws": 150,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "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": 0.49337000000000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 33.01117377347347,
      "contributing_entrants": null,
      "distinct_rated_opponents": 113,
      "draws": 509,
      "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": "2026-09-10T10:49:31Z",
      "losses": 658,
      "max_score": 44.742957151306456,
      "measured_at": null,
      "min_score": 11.223439055353664,
      "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": 92,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1698,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.8756883438432,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 33.01117377347347,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 531
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 380,
      "canonical_public_row_identity": "publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:be72f75fe8d3007b",
      "capped_draws": 75,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "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": 34.63718896016983,
      "contributing_entrants": null,
      "distinct_rated_opponents": 56,
      "draws": 129,
      "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": "2026-07-31T03:28:04Z",
      "losses": 150,
      "max_score": 57.3153424952665,
      "measured_at": null,
      "min_score": 24.0096350455345,
      "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": 93,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 380,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.0221765297592,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 32.52793710179262,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 12,
      "attempted_matches": 860,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4-nano:8753e840d1cee063",
      "capped_draws": 118,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 27
        },
        "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": 34.89630279530046,
      "contributing_entrants": null,
      "distinct_rated_opponents": 66,
      "draws": 264,
      "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": "2026-08-05T05:41:31Z",
      "losses": 336,
      "max_score": 51.6471832448803,
      "measured_at": null,
      "min_score": 12.179369637744257,
      "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": 94,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 860,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.363933510578,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 32.47466894600478,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 260
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1054,
      "canonical_public_row_identity": "publication-row.v1:mixed:x-ai-grok-4-6:aedb1b245d3cd53f",
      "capped_draws": 119,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "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": 32.338738807789284,
      "contributing_entrants": null,
      "distinct_rated_opponents": 110,
      "draws": 438,
      "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": "2026-09-10T11:06:41Z",
      "losses": 393,
      "max_score": 54.57488465434671,
      "measured_at": null,
      "min_score": 9.318441010342715,
      "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": 95,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1054,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.0219042816693,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 32.338738807789284,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 223
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 444,
      "canonical_public_row_identity": "publication-row.v1:mixed:tencent-hy3-preview:173ea133649c5bcd",
      "capped_draws": 37,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "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": 34.085726250217604,
      "contributing_entrants": null,
      "distinct_rated_opponents": 61,
      "draws": 116,
      "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": "2026-08-05T05:11:51Z",
      "losses": 187,
      "max_score": 58.73748205542807,
      "measured_at": null,
      "min_score": 7.834028495391087,
      "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": 96,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 442,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.3610026683039,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 32.010056035752946,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 139
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 339,
      "canonical_public_row_identity": "publication-row.v1:mixed:stepfun-step-3-7-flash:0e0f63cf65826515",
      "capped_draws": 52,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 20
        },
        "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": 35.767705313356814,
      "contributing_entrants": null,
      "distinct_rated_opponents": 50,
      "draws": 54,
      "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": "2026-08-05T03:50:20Z",
      "losses": 167,
      "max_score": 45.69828843610223,
      "measured_at": null,
      "min_score": 17.73358084856714,
      "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": 97,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 339,
      "rating_method": "sequential_elo",
      "raw_elo": 1389.2684513348431,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 31.8024869515411,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 118
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 898,
      "canonical_public_row_identity": "publication-row.v1:mixed:bytedance-seed-seed-2-0-code:2447db730c8d12fe",
      "capped_draws": 32,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "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": 0.42810400000000004
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 32.72437884008807,
      "contributing_entrants": null,
      "distinct_rated_opponents": 110,
      "draws": 245,
      "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": "2026-09-10T10:09:47Z",
      "losses": 334,
      "max_score": 74.84224837474918,
      "measured_at": null,
      "min_score": 5.142930493219368,
      "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": 98,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 898,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.8884134687767,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 31.649978910509514,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 319
    },
    {
      "admitted_plugins": 28,
      "attempted_matches": 3758,
      "canonical_public_row_identity": "publication-row.v1:mixed:stealth-ox-alpha:dfb3dd7361cfa1a2",
      "capped_draws": 403,
      "codegen_cost_usd": {
        "admitted_cell_count": 28,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 42
        },
        "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": 32.180212780950036,
      "contributing_entrants": null,
      "distinct_rated_opponents": 114,
      "draws": 1517,
      "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": "2026-09-10T11:06:20Z",
      "losses": 1250,
      "max_score": 49.214171810132676,
      "measured_at": null,
      "min_score": 10.84501570624497,
      "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": 99,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3751,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.2866553587492,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 31.629920879680903,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 984
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 818,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-pro:c11fecb63644464d",
      "capped_draws": 172,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "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": 33.97145389410562,
      "contributing_entrants": null,
      "distinct_rated_opponents": 110,
      "draws": 334,
      "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": "2026-09-10T11:09:42Z",
      "losses": 259,
      "max_score": 49.08988614590849,
      "measured_at": null,
      "min_score": 21.38393789540447,
      "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": 100,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 818,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.2335721457046,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 31.614000064617635,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 7,
      "attempted_matches": 584,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5:3449c1aec50b70b2",
      "capped_draws": 40,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 20
        },
        "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": 0.2141143316
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 33.58142473168707,
      "contributing_entrants": null,
      "distinct_rated_opponents": 60,
      "draws": 160,
      "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": "2026-08-05T04:57:10Z",
      "losses": 231,
      "max_score": 49.77752038298693,
      "measured_at": null,
      "min_score": 16.49481819829116,
      "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": 101,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 584,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.085119531395,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 31.536464252829603,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 193
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 963,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-terra:4506b3e0a8fb5629",
      "capped_draws": 153,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "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": 0.6137424999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 32.581399173722424,
      "contributing_entrants": null,
      "distinct_rated_opponents": 114,
      "draws": 401,
      "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": "2026-09-10T11:12:01Z",
      "losses": 306,
      "max_score": 47.20969665141295,
      "measured_at": null,
      "min_score": 9.955451026536553,
      "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": 102,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 963,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.5765046902507,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 31.51169352250512,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 256
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 404,
      "canonical_public_row_identity": "publication-row.v1:mixed:tencent-hy3-preview:7ef07d2849ca4d92",
      "capped_draws": 79,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "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": 33.64300657853923,
      "contributing_entrants": null,
      "distinct_rated_opponents": 58,
      "draws": 178,
      "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": "2026-08-05T05:08:37Z",
      "losses": 110,
      "max_score": 64.07635846709539,
      "measured_at": null,
      "min_score": 7.405950095136704,
      "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": 103,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 404,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.7454238739876,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 31.308345396792507,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 116
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 4456,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-6-flash:b574aaabaed70f28",
      "capped_draws": 596,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 29
        },
        "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": 31.213596289340646,
      "contributing_entrants": null,
      "distinct_rated_opponents": 135,
      "draws": 1589,
      "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": "2026-09-10T11:11:14Z",
      "losses": 1675,
      "max_score": 49.274306768900956,
      "measured_at": null,
      "min_score": 8.821204616548417,
      "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": 104,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 4451,
      "rating_method": "sequential_elo",
      "raw_elo": 1396.470667662523,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 31.213596289340646,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1187
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 776,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:45ec16f47504b5f5",
      "capped_draws": 150,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "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": 0.21636246784000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 33.372176280108306,
      "contributing_entrants": null,
      "distinct_rated_opponents": 113,
      "draws": 294,
      "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": "2026-09-10T11:09:23Z",
      "losses": 297,
      "max_score": 58.27831291867289,
      "measured_at": null,
      "min_score": 25.054798702264524,
      "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": 105,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 776,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.4146475615432,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 31.05630940508062,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 185
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1038,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-2:20c65e2b7513d4b4",
      "capped_draws": 176,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "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": 30.60405657846155,
      "contributing_entrants": null,
      "distinct_rated_opponents": 112,
      "draws": 335,
      "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": "2026-09-10T11:06:11Z",
      "losses": 444,
      "max_score": 54.56042710751232,
      "measured_at": null,
      "min_score": 3.385411727320254,
      "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": 106,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1038,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.8841136861088,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 30.60405657846155,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 259
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1079,
      "canonical_public_row_identity": "publication-row.v1:mixed:meta-muse-spark-1-3:22ddc49b675eb171",
      "capped_draws": 164,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "evidence_basis": "Provider-reported",
        "max": 0.043892749999999994,
        "mean": 0.023888718750000003,
        "median": 0.020423875,
        "min": 0.017614,
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.19110975
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 30.330821034598397,
      "contributing_entrants": null,
      "distinct_rated_opponents": 111,
      "draws": 388,
      "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": "2026-09-10T11:11:12Z",
      "losses": 345,
      "max_score": 45.686593077752605,
      "measured_at": null,
      "min_score": 10.355871463342384,
      "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": 107,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1071,
      "rating_method": "sequential_elo",
      "raw_elo": 1401.131294871489,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 30.330821034598397,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 8,
      "attempted_matches": 1078,
      "canonical_public_row_identity": "publication-row.v1:mixed:bytedance-seed-seed-2-0-code:c69120230888411c",
      "capped_draws": 142,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "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": 30.297799008678222,
      "contributing_entrants": null,
      "distinct_rated_opponents": 111,
      "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": "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": "2026-09-10T11:08:48Z",
      "losses": 391,
      "max_score": 49.72447731658255,
      "measured_at": null,
      "min_score": 7.518607942495322,
      "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": 1075,
      "rating_method": "sequential_elo",
      "raw_elo": 1401.9307916720434,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 30.297799008678222,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 307
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 872,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-flash:e0a2978fff9e81b1",
      "capped_draws": 154,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "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": 30.607605316675038,
      "contributing_entrants": null,
      "distinct_rated_opponents": 112,
      "draws": 380,
      "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": "2026-09-10T10:03:50Z",
      "losses": 273,
      "max_score": 73.77217005426371,
      "measured_at": null,
      "min_score": 2.2211281793648086,
      "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": 109,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 872,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.6018854928745,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 29.60270285061144,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 219
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 980,
      "canonical_public_row_identity": "publication-row.v1:mixed:thinkingmachines-inkling:a1a9848a1d14b67e",
      "capped_draws": 87,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 39
        },
        "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": 31.709014387195165,
      "contributing_entrants": null,
      "distinct_rated_opponents": 76,
      "draws": 291,
      "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": "2026-08-05T05:16:45Z",
      "losses": 403,
      "max_score": 60.57535339573391,
      "measured_at": null,
      "min_score": 12.336409573070739,
      "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": 110,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 980,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.1747761848974,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 29.508562866062203,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 286
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1178,
      "canonical_public_row_identity": "publication-row.v1:mixed:meituan-longcat-2-0:45102822fc5f9296",
      "capped_draws": 236,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 38
        },
        "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": 30.345518662237996,
      "contributing_entrants": null,
      "distinct_rated_opponents": 76,
      "draws": 415,
      "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": "2026-08-05T05:24:42Z",
      "losses": 444,
      "max_score": 44.89316223345493,
      "measured_at": null,
      "min_score": 8.990579277651428,
      "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": 111,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1174,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.294317219309,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 29.3492209701396,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 315
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 512,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-1-flash-lite:4c9cdde1729642af",
      "capped_draws": 71,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "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": 0.08108399999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 31.22469222252498,
      "contributing_entrants": null,
      "distinct_rated_opponents": 59,
      "draws": 128,
      "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": "2026-08-05T05:18:42Z",
      "losses": 245,
      "max_score": 42.02538255150319,
      "measured_at": null,
      "min_score": 13.765200753063453,
      "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": 112,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 510,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.138297710363,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 29.057850306249282,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 137
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 762,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-flash:dac448fbfe2a5737",
      "capped_draws": 130,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 24
        },
        "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": 0.050973330659999996
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 29.891312868171436,
      "contributing_entrants": null,
      "distinct_rated_opponents": 62,
      "draws": 264,
      "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": "2026-07-31T20:22:51Z",
      "losses": 309,
      "max_score": 41.566578731207976,
      "measured_at": null,
      "min_score": 11.325590947035412,
      "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": 113,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 762,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.1094312327036,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 28.909927565259828,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 189
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 898,
      "canonical_public_row_identity": "publication-row.v1:mixed:meta-muse-glimmer-30b:085624a1bd2a3883",
      "capped_draws": 177,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "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": 29.80850611716221,
      "contributing_entrants": null,
      "distinct_rated_opponents": 111,
      "draws": 410,
      "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": "2026-09-10T11:07:30Z",
      "losses": 266,
      "max_score": 49.03370945933072,
      "measured_at": null,
      "min_score": 8.569180028204126,
      "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": 114,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 898,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.7481350106614,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 28.829839508099237,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 5,
      "attempted_matches": 364,
      "canonical_public_row_identity": "publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:a3e60c7aa64704be",
      "capped_draws": 68,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 21
        },
        "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": 33.17879341527922,
      "contributing_entrants": null,
      "distinct_rated_opponents": 58,
      "draws": 135,
      "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": "2026-08-05T03:41:43Z",
      "losses": 127,
      "max_score": 58.942903698869344,
      "measured_at": null,
      "min_score": 10.53671511272001,
      "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": 115,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 364,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.7703846459403,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 28.644580216192928,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 102
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1123,
      "canonical_public_row_identity": "publication-row.v1:mixed:thinkingmachines-inkling-small:c4a079d6b58a2c73",
      "capped_draws": 170,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "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": 0.38761485
      },
      "codegen_evaluated_cells": 10,
      "conditional_success_score": 30.174245478812885,
      "contributing_entrants": null,
      "distinct_rated_opponents": 106,
      "draws": 426,
      "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": "2026-09-10T10:55:16Z",
      "losses": 362,
      "max_score": 49.240345149208736,
      "measured_at": null,
      "min_score": 10.341010847452775,
      "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": 116,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1123,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.566408918735,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 28.537039469589303,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 335
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 560,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4-mini:9285646640165917",
      "capped_draws": 85,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "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": 28.42341314043818,
      "contributing_entrants": null,
      "distinct_rated_opponents": 58,
      "draws": 250,
      "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": "2026-08-05T05:24:08Z",
      "losses": 205,
      "max_score": 39.92088394835182,
      "measured_at": null,
      "min_score": 12.418449045966476,
      "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": 117,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 556,
      "rating_method": "sequential_elo",
      "raw_elo": 1383.8728599981719,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 28.42341314043818,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 101
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 566,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5:32918e3c3e0fca83",
      "capped_draws": 47,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 32
        },
        "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": 0.27207317540000003
      },
      "codegen_evaluated_cells": 12,
      "conditional_success_score": 30.858150991428047,
      "contributing_entrants": null,
      "distinct_rated_opponents": 58,
      "draws": 262,
      "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": "2026-07-31T03:36:31Z",
      "losses": 187,
      "max_score": 54.43964322154773,
      "measured_at": null,
      "min_score": 13.893411007112569,
      "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": 118,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 566,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.4344299456152,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 27.883487063549502,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 117
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 349,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-1-flash-lite:78a7cfd3a790e8a8",
      "capped_draws": 54,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "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": 31.10122013544669,
      "contributing_entrants": null,
      "distinct_rated_opponents": 55,
      "draws": 101,
      "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": "2026-08-05T05:05:18Z",
      "losses": 179,
      "max_score": 45.56327909407335,
      "measured_at": null,
      "min_score": 24.238563997706606,
      "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": 119,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 349,
      "rating_method": "sequential_elo",
      "raw_elo": 1364.6887064246337,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 27.653329696976403,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 3294,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-5-flash-lite:5943a501fa6113ab",
      "capped_draws": 274,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 50
        },
        "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": 0.9722945
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 28.216737067230966,
      "contributing_entrants": null,
      "distinct_rated_opponents": 126,
      "draws": 883,
      "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": "2026-09-10T11:08:35Z",
      "losses": 1385,
      "max_score": 48.1277645295087,
      "measured_at": null,
      "min_score": 12.3621226468018,
      "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": 120,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3292,
      "rating_method": "sequential_elo",
      "raw_elo": 1367.6718240595555,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 27.290331085130802,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1024
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1064,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-flash:e1a2822fb5bba20e",
      "capped_draws": 167,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "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": 26.70950374619811,
      "contributing_entrants": null,
      "distinct_rated_opponents": 111,
      "draws": 435,
      "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": "2026-09-10T11:08:14Z",
      "losses": 420,
      "max_score": 52.04746013492715,
      "measured_at": null,
      "min_score": 8.345895178371906,
      "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": 121,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1064,
      "rating_method": "sequential_elo",
      "raw_elo": 1357.1212983556989,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 26.70950374619811,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 209
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 908,
      "canonical_public_row_identity": "publication-row.v1:mixed:openai-gpt-oss-120b:7e4ecfa424847773",
      "capped_draws": 130,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "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": 0.059539762
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 27.433152416942608,
      "contributing_entrants": null,
      "distinct_rated_opponents": 109,
      "draws": 386,
      "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": "2026-09-10T10:49:44Z",
      "losses": 305,
      "max_score": 53.690628075980555,
      "measured_at": null,
      "min_score": 12.913154477319852,
      "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": 122,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 907,
      "rating_method": "sequential_elo",
      "raw_elo": 1373.725766506921,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 26.532472921423064,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 216
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 282,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5:024b37c390436d5a",
      "capped_draws": 92,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "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": 0.19736108440000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 29.66033164309214,
      "contributing_entrants": null,
      "distinct_rated_opponents": 53,
      "draws": 178,
      "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": "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": "2026-07-31T20:22:54Z",
      "losses": 63,
      "max_score": 55.88030293196678,
      "measured_at": null,
      "min_score": 14.876831236011256,
      "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": 123,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 282,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.0182986919922,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 26.37217852791834,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 9,
      "attempted_matches": 573,
      "canonical_public_row_identity": "publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:94c7956182cf2d89",
      "capped_draws": 115,
      "codegen_cost_usd": {
        "admitted_cell_count": 9,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 35
        },
        "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": 30.26933128936782,
      "contributing_entrants": null,
      "distinct_rated_opponents": 63,
      "draws": 252,
      "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": "2026-08-05T04:29:54Z",
      "losses": 196,
      "max_score": 47.23542996577578,
      "measured_at": null,
      "min_score": 11.68296478061394,
      "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": 124,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 573,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.6288767387816,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 26.21400985215971,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 125
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 576,
      "canonical_public_row_identity": "publication-row.v1:mixed:minimax-minimax-m3:6f48906184a5bdb8",
      "capped_draws": 78,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "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": 27.094189624924688,
      "contributing_entrants": null,
      "distinct_rated_opponents": 61,
      "draws": 191,
      "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": "2026-08-05T04:04:06Z",
      "losses": 262,
      "max_score": 48.5556009285104,
      "measured_at": null,
      "min_score": 5.046768034226976,
      "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": 125,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 576,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.5000954323484,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 26.204638884565124,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 123
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 996,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-2:184634950256ca6a",
      "capped_draws": 154,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "evidence_basis": "Provider-reported",
        "max": 0.050486600000000006,
        "mean": 0.0257422554375,
        "median": 0.02408436405,
        "min": 0.0093287,
        "recorded_attempt_count": 13,
        "run_count": 8,
        "total": 0.20593804350000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 26.018709691140266,
      "contributing_entrants": null,
      "distinct_rated_opponents": 105,
      "draws": 395,
      "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": "2026-09-10T11:06:45Z",
      "losses": 359,
      "max_score": 51.1220637969503,
      "measured_at": null,
      "min_score": 8.040430110624992,
      "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": 126,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 996,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.9771151413718,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 26.018709691140266,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 242
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 926,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-flash:04d7da5a4f2e2af2",
      "capped_draws": 120,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "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": 26.614508029189267,
      "contributing_entrants": null,
      "distinct_rated_opponents": 108,
      "draws": 283,
      "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": "2026-09-10T11:06:06Z",
      "losses": 371,
      "max_score": 48.009788801136246,
      "measured_at": null,
      "min_score": 8.085742846285687,
      "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": 127,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 926,
      "rating_method": "sequential_elo",
      "raw_elo": 1341.127056397135,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 25.740706094183555,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 272
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 368,
      "canonical_public_row_identity": "publication-row.v1:mixed:nex-agi-nex-n2-pro:a8c61d4550659ad0",
      "capped_draws": 14,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "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": 28.879374910115267,
      "contributing_entrants": null,
      "distinct_rated_opponents": 58,
      "draws": 43,
      "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": "2026-08-05T05:35:20Z",
      "losses": 223,
      "max_score": 47.74072823827207,
      "measured_at": null,
      "min_score": 7.328898964258992,
      "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": 128,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 368,
      "rating_method": "sequential_elo",
      "raw_elo": 1323.9636857229561,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 25.677798888726322,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 102
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 3264,
      "canonical_public_row_identity": "publication-row.v1:mixed:meituan-longcat-2-0:bed5035a5082adf8",
      "capped_draws": 231,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 70
        },
        "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": 27.242268163777958,
      "contributing_entrants": null,
      "distinct_rated_opponents": 139,
      "draws": 862,
      "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": "2026-09-10T10:39:01Z",
      "losses": 1567,
      "max_score": 42.612280911763705,
      "measured_at": null,
      "min_score": 5.565460776989309,
      "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": 129,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3230,
      "rating_method": "sequential_elo",
      "raw_elo": 1371.1939426278043,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 25.351787126174198,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 33,
      "wins": 801
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 432,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-7-plus:cdc5232f1e60910a",
      "capped_draws": 22,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "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": 27.57407026128659,
      "contributing_entrants": null,
      "distinct_rated_opponents": 59,
      "draws": 143,
      "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": "2026-08-05T03:19:33Z",
      "losses": 189,
      "max_score": 50.37567398128637,
      "measured_at": null,
      "min_score": 14.181701766649182,
      "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": 130,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 430,
      "rating_method": "sequential_elo",
      "raw_elo": 1368.1228288641923,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 24.9159851357772,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 98
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 990,
      "canonical_public_row_identity": "publication-row.v1:mixed:openai-gpt-oss-120b:59563b7e90e4a253",
      "capped_draws": 162,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "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": 24.648172544378482,
      "contributing_entrants": null,
      "distinct_rated_opponents": 104,
      "draws": 400,
      "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": "2026-09-10T10:52:53Z",
      "losses": 376,
      "max_score": 38.95744773414053,
      "measured_at": null,
      "min_score": 9.805861440635663,
      "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": 131,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 990,
      "rating_method": "sequential_elo",
      "raw_elo": 1330.7221983901602,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 24.648172544378482,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 214
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 750,
      "canonical_public_row_identity": "publication-row.v1:mixed:meta-muse-glimmer-30b:a614a905445f79d1",
      "capped_draws": 162,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "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": 26.077506622187926,
      "contributing_entrants": null,
      "distinct_rated_opponents": 111,
      "draws": 282,
      "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": "2026-09-10T11:05:42Z",
      "losses": 301,
      "max_score": 37.00463002835304,
      "measured_at": null,
      "min_score": 6.990073492948425,
      "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": 132,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 750,
      "rating_method": "sequential_elo",
      "raw_elo": 1318.3136365028786,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 24.267854375875263,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 167
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 750,
      "canonical_public_row_identity": "publication-row.v1:mixed:openai-gpt-oss-120b:07d17099885c6bdb",
      "capped_draws": 143,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "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": 0.009855890999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 25.417909395473753,
      "contributing_entrants": null,
      "distinct_rated_opponents": 101,
      "draws": 292,
      "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": "2026-09-10T11:05:48Z",
      "losses": 268,
      "max_score": 40.640073310441565,
      "measured_at": null,
      "min_score": 9.761584645888398,
      "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": 133,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 750,
      "rating_method": "sequential_elo",
      "raw_elo": 1341.9142700886227,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 23.654029991644784,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 190
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 864,
      "canonical_public_row_identity": "publication-row.v1:mixed:bytedance-seed-seed-2-0-code:e037862ab5c7ecb3",
      "capped_draws": 162,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "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": 0.16760899999999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 23.90857395896249,
      "contributing_entrants": null,
      "distinct_rated_opponents": 113,
      "draws": 289,
      "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": "2026-09-10T11:06:39Z",
      "losses": 398,
      "max_score": 34.82242746606155,
      "measured_at": null,
      "min_score": 14.961257423631709,
      "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": 134,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 858,
      "rating_method": "sequential_elo",
      "raw_elo": 1276.554271400966,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 23.12361268274216,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 171
    },
    {
      "admitted_plugins": 9,
      "attempted_matches": 2368,
      "canonical_public_row_identity": "publication-row.v1:mixed:thinkingmachines-inkling:281eafa14f6ff011",
      "capped_draws": 303,
      "codegen_cost_usd": {
        "admitted_cell_count": 9,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 53
        },
        "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": 26.43318592739723,
      "contributing_entrants": null,
      "distinct_rated_opponents": 126,
      "draws": 773,
      "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": "2026-09-10T11:08:22Z",
      "losses": 1108,
      "max_score": 55.3334397747058,
      "measured_at": null,
      "min_score": 9.050334687326071,
      "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": 135,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2366,
      "rating_method": "sequential_elo",
      "raw_elo": 1340.9913264100708,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 22.891810516083325,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 485
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": 2985,
      "canonical_public_row_identity": "publication-row.v1:mixed:poolside-laguna-s-2-1:07eac22bdea1b9b3",
      "capped_draws": 498,
      "codegen_cost_usd": {
        "admitted_cell_count": 11,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 35
        },
        "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": 0.04917796000000001
      },
      "codegen_evaluated_cells": 14,
      "conditional_success_score": 24.290531112031516,
      "contributing_entrants": null,
      "distinct_rated_opponents": 140,
      "draws": 1302,
      "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": "2026-09-10T10:57:42Z",
      "losses": 1119,
      "max_score": 40.16991479649198,
      "measured_at": null,
      "min_score": 11.01099847514966,
      "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": 136,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2985,
      "rating_method": "sequential_elo",
      "raw_elo": 1342.6238101954334,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 22.86931587697147,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 564
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 958,
      "canonical_public_row_identity": "publication-row.v1:mixed:meta-muse-glimmer-30b:20d2aea9e268d0ef",
      "capped_draws": 161,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "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": 22.81328793344419,
      "contributing_entrants": null,
      "distinct_rated_opponents": 100,
      "draws": 407,
      "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": "2026-09-10T10:55:16Z",
      "losses": 346,
      "max_score": 39.83813064889331,
      "measured_at": null,
      "min_score": 8.950914647096557,
      "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": 137,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 958,
      "rating_method": "sequential_elo",
      "raw_elo": 1310.9758552377175,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 22.81328793344419,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 205
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 3581,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-5-flash-lite:0bab1c3ea19c7cb7",
      "capped_draws": 593,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 48
        },
        "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": 23.147895521816984,
      "contributing_entrants": null,
      "distinct_rated_opponents": 155,
      "draws": 1277,
      "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": "2026-09-10T11:06:31Z",
      "losses": 1589,
      "max_score": 39.89414504066892,
      "measured_at": null,
      "min_score": 11.967580414073916,
      "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": 138,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3571,
      "rating_method": "sequential_elo",
      "raw_elo": 1300.4728466012357,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 22.38790868020074,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 705
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 642,
      "canonical_public_row_identity": "publication-row.v1:mixed:inception-mercury-2-5-preview:df3dbf369397b893",
      "capped_draws": 11,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "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": 23.962159689024865,
      "contributing_entrants": null,
      "distinct_rated_opponents": 109,
      "draws": 258,
      "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": "2026-09-10T10:05:55Z",
      "losses": 217,
      "max_score": 39.11032563550241,
      "measured_at": null,
      "min_score": 11.73718454940338,
      "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": 139,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 641,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.8631378590524,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 21.305707597528798,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 8,
      "attempted_matches": 1198,
      "canonical_public_row_identity": "publication-row.v1:mixed:thinkingmachines-inkling-small:6603774c29b8a046",
      "capped_draws": 135,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "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": 0.07763975000000001
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 21.132069816135214,
      "contributing_entrants": null,
      "distinct_rated_opponents": 113,
      "draws": 409,
      "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": "2026-09-10T10:54:12Z",
      "losses": 543,
      "max_score": 54.086740109183,
      "measured_at": null,
      "min_score": 0.0,
      "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": 140,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1198,
      "rating_method": "sequential_elo",
      "raw_elo": 1286.4616974117926,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 20.518892029756675,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 246
    },
    {
      "admitted_plugins": 10,
      "attempted_matches": 1068,
      "canonical_public_row_identity": "publication-row.v1:mixed:inclusionai-ling-3-0-flash:1ed2a890413ad375",
      "capped_draws": 289,
      "codegen_cost_usd": {
        "admitted_cell_count": 10,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 40
        },
        "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": 22.86688675022906,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 533,
      "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": "2026-08-05T05:41:59Z",
      "losses": 359,
      "max_score": 37.1347934270453,
      "measured_at": null,
      "min_score": 7.0150208382150785,
      "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": 141,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1066,
      "rating_method": "sequential_elo",
      "raw_elo": 1360.6475316318747,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 20.331856939812095,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 174
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1116,
      "canonical_public_row_identity": "publication-row.v1:mixed:thinkingmachines-inkling-small:f1451a0a6af20650",
      "capped_draws": 166,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "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": 20.689010458032868,
      "contributing_entrants": null,
      "distinct_rated_opponents": 106,
      "draws": 482,
      "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": "2026-09-10T11:11:12Z",
      "losses": 442,
      "max_score": 31.934103720162618,
      "measured_at": null,
      "min_score": 0.0,
      "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": 142,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1115,
      "rating_method": "sequential_elo",
      "raw_elo": 1273.991138220205,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 20.08868868428344,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 191
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 290,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-1-flash-lite:f12274812b7e4c60",
      "capped_draws": 19,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "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": 0.047068750000000006
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 21.823970921280427,
      "contributing_entrants": null,
      "distinct_rated_opponents": 54,
      "draws": 67,
      "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": "2026-07-31T03:34:49Z",
      "losses": 167,
      "max_score": 39.06289260104517,
      "measured_at": null,
      "min_score": 14.474268235287061,
      "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": 143,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 290,
      "rating_method": "sequential_elo",
      "raw_elo": 1270.8645282982493,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 19.404559067300582,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 722,
      "canonical_public_row_identity": "publication-row.v1:mixed:inception-mercury-2-5-preview:f07bc2e66f8341c5",
      "capped_draws": 117,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "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": 0.010122239999999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 19.044072383738698,
      "contributing_entrants": null,
      "distinct_rated_opponents": 96,
      "draws": 315,
      "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": "2026-09-10T10:39:00Z",
      "losses": 306,
      "max_score": 30.71080462121027,
      "measured_at": null,
      "min_score": 6.865539546300709,
      "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": 144,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 721,
      "rating_method": "sequential_elo",
      "raw_elo": 1275.7209898590386,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 17.722506297399335,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 100
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 718,
      "canonical_public_row_identity": "publication-row.v1:mixed:inception-mercury-2-5-preview:ff9c957a999941a2",
      "capped_draws": 130,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "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": 17.46211413058019,
      "contributing_entrants": null,
      "distinct_rated_opponents": 106,
      "draws": 323,
      "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": "2026-09-10T11:05:37Z",
      "losses": 317,
      "max_score": 24.270432377976235,
      "measured_at": null,
      "min_score": 10.683228762592293,
      "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": 145,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 718,
      "rating_method": "sequential_elo",
      "raw_elo": 1259.6489304042077,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 16.25032826011336,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1604,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-luna:15a0f0a09f9eb8e5",
      "capped_draws": 104,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "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": 0.036787799999999996
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 16.090509598812808,
      "contributing_entrants": null,
      "distinct_rated_opponents": 106,
      "draws": 526,
      "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": "2026-09-10T11:01:22Z",
      "losses": 845,
      "max_score": 24.54821424333988,
      "measured_at": null,
      "min_score": 0.0,
      "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": 146,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1604,
      "rating_method": "sequential_elo",
      "raw_elo": 1228.9818249502457,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 16.090509598812808,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 233
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 844,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-3:650c1432bdd4728a",
      "capped_draws": 10,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "evidence_basis": "Provider-reported",
        "max": 0.5256212,
        "mean": 0.38805244562499996,
        "median": 0.41839404999999996,
        "min": 0.063446985,
        "recorded_attempt_count": 8,
        "run_count": 8,
        "total": 3.1044195650000006
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 78.85594773673789,
      "contributing_entrants": null,
      "distinct_rated_opponents": 95,
      "draws": 101,
      "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": "2026-09-10T11:05:19Z",
      "losses": 112,
      "max_score": 98.77394998739801,
      "measured_at": null,
      "min_score": 35.48069279237866,
      "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": 838,
      "rating_method": "sequential_elo",
      "raw_elo": 1928.1620525983792,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 78.85594773673789,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 625
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 724,
      "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
        },
        "evidence_basis": "Provider-reported",
        "max": 0.273243,
        "mean": 0.18666160714285715,
        "median": 0.20966,
        "min": 0.0,
        "recorded_attempt_count": 7,
        "run_count": 7,
        "total": 1.3066312500000001
      },
      "codegen_evaluated_cells": 6,
      "conditional_success_score": 54.944564738186564,
      "contributing_entrants": null,
      "distinct_rated_opponents": 104,
      "draws": 131,
      "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": "2026-09-10T11:11:14Z",
      "losses": 252,
      "max_score": 79.56504037106075,
      "measured_at": null,
      "min_score": 18.420844285465474,
      "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": 723,
      "rating_method": "sequential_elo",
      "raw_elo": 1679.467858899104,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 54.944564738186564,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 340
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 420,
      "canonical_public_row_identity": "publication-row.v1:mixed:meta-muse-spark-1-2:c4024993f2e98d89",
      "capped_draws": 33,
      "codegen_cost_usd": {
        "admitted_cell_count": 2,
        "cell_count": 2,
        "cost_basis_counts": {
          "provider_reported": 2
        },
        "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": 43.05120520009523,
      "contributing_entrants": null,
      "distinct_rated_opponents": 95,
      "draws": 51,
      "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": "2026-09-10T11:05:40Z",
      "losses": 190,
      "max_score": 51.675962062161574,
      "measured_at": null,
      "min_score": 34.42644833802889,
      "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": 420,
      "rating_method": "sequential_elo",
      "raw_elo": 1524.937926280082,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 43.05120520009523,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 179
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2170,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-5:e2ff6744eb1bb7c6",
      "capped_draws": 116,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "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": 1.42452
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.43578753789422,
      "contributing_entrants": null,
      "distinct_rated_opponents": 143,
      "draws": 517,
      "eligibility_flag": false,
      "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": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-10T11:09:47Z",
      "losses": 753,
      "max_score": 59.105299689263475,
      "measured_at": null,
      "min_score": 9.845278217768804,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 2168,
      "rating_method": "sequential_elo",
      "raw_elo": 1528.1701319696285,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 42.43578753789422,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 898
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 398,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:4b9c2bdb10b14302",
      "capped_draws": 54,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "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": 44.10609034219564,
      "contributing_entrants": null,
      "distinct_rated_opponents": 57,
      "draws": 92,
      "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-v2.5-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": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:11:01Z",
      "losses": 152,
      "max_score": 70.02330483752023,
      "measured_at": null,
      "min_score": 27.56700348772194,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 398,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.351739327467,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 41.04534198844345,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 154
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 1314,
      "canonical_public_row_identity": "publication-row.v1:mixed:moonshotai-kimi-k3:ccf8a3c1c9260d55",
      "capped_draws": 38,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "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": 4.208937
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 44.59194591921063,
      "contributing_entrants": null,
      "distinct_rated_opponents": 119,
      "draws": 413,
      "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": "2026-09-10T11:06:10Z",
      "losses": 419,
      "max_score": 65.77337510145159,
      "measured_at": null,
      "min_score": 13.442672880681176,
      "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": 1302,
      "rating_method": "sequential_elo",
      "raw_elo": 1555.769339523801,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 40.99438879961144,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 470
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 17
        },
        "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": 40.741749761275216,
      "contributing_entrants": null,
      "distinct_rated_opponents": 61,
      "draws": 281,
      "eligibility_flag": false,
      "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": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-31T20:22:43Z",
      "losses": 250,
      "max_score": 58.364933687116554,
      "measured_at": null,
      "min_score": 13.80218482679183,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 804,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.1693401730854,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 40.08967135973522,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 273
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 334,
      "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
        },
        "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": 42.37685841855066,
      "contributing_entrants": null,
      "distinct_rated_opponents": 54,
      "draws": 55,
      "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": "2026-08-05T03:57:18Z",
      "losses": 143,
      "max_score": 57.095657519959566,
      "measured_at": null,
      "min_score": 27.208177713775562,
      "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": 332,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.5393162508012,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 36.84420968400358,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 134
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 438,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:36d8ebdcb946256c",
      "capped_draws": 30,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 7,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.1311545862,
        "mean": 0.02955606902857143,
        "median": 0.0063034062,
        "min": 0.0057139812,
        "recorded_attempt_count": 10,
        "run_count": 7,
        "total": 0.2068924832
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 37.32543758140332,
      "contributing_entrants": null,
      "distinct_rated_opponents": 55,
      "draws": 104,
      "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": "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": 0.5714285714285714,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_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": "2026-08-05T04:19:05Z",
      "losses": 166,
      "max_score": 53.03980999081365,
      "measured_at": null,
      "min_score": 16.473094673491183,
      "model_code_failure_rate": 0.14285714285714285,
      "model_code_failures": 1,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": 0.8571428571428571,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 438,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.0654512452504,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 0.2857142857142857,
      "results_cut_id": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 35.91436651599566,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 168
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-4-1-nano:68d5f0be3c90fb50",
      "capped_draws": 65,
      "codegen_cost_usd": {
        "admitted_cell_count": 1,
        "cell_count": 1,
        "cost_basis_counts": {
          "estimated": 1,
          "local_standard_estimate": 1
        },
        "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": 35.18099307381629,
      "contributing_entrants": null,
      "distinct_rated_opponents": 91,
      "draws": 65,
      "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": "2026-09-10T04:08:50Z",
      "losses": 103,
      "max_score": 35.18099307381629,
      "measured_at": null,
      "min_score": 35.18099307381629,
      "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": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 1388.89236890581,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 35.18099307381629,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2248,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-5:9f0371e603fb81bd",
      "capped_draws": 247,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "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": 35.14311845280274,
      "contributing_entrants": null,
      "distinct_rated_opponents": 127,
      "draws": 705,
      "eligibility_flag": false,
      "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": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-10T11:11:52Z",
      "losses": 809,
      "max_score": 54.54022332767149,
      "measured_at": null,
      "min_score": 4.775250900350241,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 2248,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.3209470524448,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 35.14311845280274,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 734
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 693,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-27b:47ad2584aeb815bb",
      "capped_draws": 78,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "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": 34.62654964999745,
      "contributing_entrants": null,
      "distinct_rated_opponents": 110,
      "draws": 120,
      "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": "2026-09-10T11:11:56Z",
      "losses": 322,
      "max_score": 50.69846903136761,
      "measured_at": null,
      "min_score": 18.985013985665347,
      "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": 692,
      "rating_method": "sequential_elo",
      "raw_elo": 1362.3511931585113,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 31.832973643106108,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 250
    },
    {
      "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
        },
        "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": 33.971196577578915,
      "contributing_entrants": null,
      "distinct_rated_opponents": 58,
      "draws": 147,
      "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": "2026-08-05T05:19:01Z",
      "losses": 190,
      "max_score": 49.11080098947388,
      "measured_at": null,
      "min_score": 22.98682614510266,
      "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": 486,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.5536195326868,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 31.613760604607553,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 149
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 474,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemma-4-31b-it:e2b2f6f0f78a1f3f",
      "capped_draws": 85,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 7,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "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": 32.242665330503485,
      "contributing_entrants": null,
      "distinct_rated_opponents": 57,
      "draws": 142,
      "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": "2026-08-05T03:48:11Z",
      "losses": 198,
      "max_score": 47.537908439761935,
      "measured_at": null,
      "min_score": 24.766615824644276,
      "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": 472,
      "rating_method": "sequential_elo",
      "raw_elo": 1374.7432089327137,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 31.023746141136392,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 132
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 1110,
      "canonical_public_row_identity": "publication-row.v1:mixed:stepfun-step-3-7-flash:b2de164dfb65fa47",
      "capped_draws": 192,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 20
        },
        "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": 35.63407345020555,
      "contributing_entrants": null,
      "distinct_rated_opponents": 118,
      "draws": 216,
      "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": "2026-09-10T11:06:38Z",
      "losses": 519,
      "max_score": 47.765690377579354,
      "measured_at": null,
      "min_score": 20.829015374383967,
      "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": 1106,
      "rating_method": "sequential_elo",
      "raw_elo": 1357.5958608523906,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 29.96456462516541,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 371
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 476,
      "canonical_public_row_identity": "publication-row.v1:mixed:nex-agi-nex-n2-pro:b04b6e7c11ec4633",
      "capped_draws": 77,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 36
        },
        "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": 34.363072647101255,
      "contributing_entrants": null,
      "distinct_rated_opponents": 59,
      "draws": 222,
      "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": "2026-08-05T04:41:06Z",
      "losses": 137,
      "max_score": 60.77934776395481,
      "measured_at": null,
      "min_score": 12.252825466946847,
      "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": 476,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.5851529093154,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 27.947084277846592,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 117
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 320,
      "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
        },
        "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": 31.49301590711204,
      "contributing_entrants": null,
      "distinct_rated_opponents": 55,
      "draws": 120,
      "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": "2026-08-05T05:11:10Z",
      "losses": 120,
      "max_score": 49.98510602874532,
      "measured_at": null,
      "min_score": 15.266282350907517,
      "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": 320,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.6971779128244,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 26.48236418181872,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1022,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-5-flash:e1e7937be001cd2a",
      "capped_draws": 151,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 11
        },
        "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": 23.68539356485576,
      "contributing_entrants": null,
      "distinct_rated_opponents": 111,
      "draws": 384,
      "eligibility_flag": false,
      "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": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-10T11:08:37Z",
      "losses": 384,
      "max_score": 52.643022639184814,
      "measured_at": null,
      "min_score": 8.860426297576485,
      "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": 1022,
      "rating_method": "sequential_elo",
      "raw_elo": 1335.8563162445548,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 23.68539356485576,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 254
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 1110,
      "canonical_public_row_identity": "publication-row.v1:mixed:o3:29970c6bc7db3c37",
      "capped_draws": 289,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "estimated": 8,
          "local_standard_estimate": 13
        },
        "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": 26.102373200502253,
      "contributing_entrants": null,
      "distinct_rated_opponents": 117,
      "draws": 329,
      "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": "2026-09-10T10:03:47Z",
      "losses": 564,
      "max_score": 44.781096360775045,
      "measured_at": null,
      "min_score": 13.652811210043236,
      "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": 1110,
      "rating_method": "sequential_elo",
      "raw_elo": 1254.6346491602558,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 21.94939205391697,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 217
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 428,
      "canonical_public_row_identity": "publication-row.v1:mixed:cohere-north-mini-code:4a23759df70ab26b",
      "capped_draws": 156,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 30
        },
        "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": 29.334470894205833,
      "contributing_entrants": null,
      "distinct_rated_opponents": 60,
      "draws": 156,
      "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": "2026-08-05T05:09:16Z",
      "losses": 198,
      "max_score": 33.07868627119113,
      "measured_at": null,
      "min_score": 26.207095835838984,
      "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": 424,
      "rating_method": "sequential_elo",
      "raw_elo": 1334.5884303676582,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 21.93263264971003,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 70
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1367,
      "canonical_public_row_identity": "publication-row.v1:mixed:thinkingmachines-inkling:b27963da4b6944f2",
      "capped_draws": 268,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 53
        },
        "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": 26.69039305708575,
      "contributing_entrants": null,
      "distinct_rated_opponents": 151,
      "draws": 495,
      "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": "2026-09-10T10:39:04Z",
      "losses": 588,
      "max_score": 43.70587386646689,
      "measured_at": null,
      "min_score": 15.613204983285852,
      "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": 1364,
      "rating_method": "sequential_elo",
      "raw_elo": 1322.6602659949974,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 20.886361304870018,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 281
    },
    {
      "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
        },
        "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": 23.90120559075741,
      "contributing_entrants": null,
      "distinct_rated_opponents": 126,
      "draws": 467,
      "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": "2026-09-10T10:27:32Z",
      "losses": 783,
      "max_score": 43.412761651647685,
      "measured_at": null,
      "min_score": 6.242872745526706,
      "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": 1620,
      "rating_method": "sequential_elo",
      "raw_elo": 1364.6961632417467,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 19.00792918857275,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 370
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-27b:3dc939e9daa83d91",
      "capped_draws": 101,
      "codegen_cost_usd": {
        "admitted_cell_count": 3,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "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": 23.705963362379308,
      "contributing_entrants": null,
      "distinct_rated_opponents": 89,
      "draws": 180,
      "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": "2026-09-10T11:06:09Z",
      "losses": 52,
      "max_score": 24.392761540116325,
      "measured_at": null,
      "min_score": 23.019165184642294,
      "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": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.1571286454732,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 18.550918857121076,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 22,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "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
        },
        "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": 20.32563417683313,
      "contributing_entrants": null,
      "distinct_rated_opponents": 57,
      "draws": 101,
      "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": "2026-09-10T11:00:35Z",
      "losses": 30,
      "max_score": 20.32563417683313,
      "measured_at": null,
      "min_score": 20.32563417683313,
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1328.441766750424,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 12.085694390016217,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-row.v1:mixed:ibm-granite-granite-4-2-8b:49a29e6f1bedcd1d",
      "capped_draws": 105,
      "codegen_cost_usd": {
        "admitted_cell_count": 2,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "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": 10.934934183457305,
      "contributing_entrants": null,
      "distinct_rated_opponents": 77,
      "draws": 105,
      "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": "2026-09-10T11:06:08Z",
      "losses": 137,
      "max_score": 21.86986836691461,
      "measured_at": null,
      "min_score": 0.0,
      "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": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1109.390743883938,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 7.732166112951243,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1,
      "attempted_matches": 202,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-4:672219b99ff5a80c",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "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-5.4",
        "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": "2026-09-10T10:25:37Z",
      "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": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 2181.186817301249,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 202,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-4:483e8409583d40a0",
      "capped_draws": 4,
      "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": "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": 11,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:09Z",
      "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": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 2082.5792261697334,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 91.89049593436994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 118,
      "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": 59,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:14Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 2056.7386464310007,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 89.05863634547586,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 113
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-6-astra:8883275fa81b106a",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "draws": 5,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-09-10T10:09:34Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1993.4538122220206,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 83.85408145856084,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 100
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-5-flash:188028ef432c73f8",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "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": "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": 18,
      "max_score": null,
      "measured_at": "2026-09-10T10:09:43Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1971.1902035562755,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 82.02311872112153,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:z-ai-glm-5-3:650c1432bdd4728a",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "draws": 10,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-09-10T10:10:04Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1940.1681080558346,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 79.47185662559322,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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": 26,
      "max_score": null,
      "measured_at": "2026-09-10T10:09:07Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1925.0620812038217,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 78.22953456127536,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "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": 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": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-09-10T10:15:28Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1915.473139954479,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 77.44093849930564,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 92
    },
    {
      "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": 17,
      "max_score": null,
      "measured_at": "2026-09-10T10:09:13Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1909.6549229355353,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 76.96244740112121,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 100
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 200,
      "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": 80,
      "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": 58,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:07Z",
      "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": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1883.3980174205028,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 75.49834308214069,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:x-ai-grok-4-5:5e133fd8ec34ed0c",
      "capped_draws": 56,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 94,
      "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": "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": 31,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:31Z",
      "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": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1851.5695914706555,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 73.17261948899618,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 203,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-sol:e7389fafab42de55",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "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-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": 61,
      "max_score": null,
      "measured_at": "2026-09-10T11:12:01Z",
      "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": 203,
      "rating_method": "sequential_elo",
      "raw_elo": 1828.5102740039317,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 71.00149057401816,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:x-ai-grok-4-5:a7aa1873ad17dbcc",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 7,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-08-03T18:34:47Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1796.9255894755222,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 66.95829181437593,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 2,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 198,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:meta-muse-spark-1-2:0ef600658249027b",
      "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": "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": 45,
      "max_score": null,
      "measured_at": "2026-09-10T09:56:02Z",
      "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": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1746.306694043386,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 64.21230002498487,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 204,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-4:cea8a68bd875deb9",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "draws": 15,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:29Z",
      "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": 204,
      "rating_method": "sequential_elo",
      "raw_elo": 1744.6628933313261,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 64.11149296941215,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:tencent-hy3-preview:7ef07d2849ca4d92",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 12,
      "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": 7,
      "max_score": null,
      "measured_at": "2026-08-05T05:08:37Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1765.1662409309436,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 64.07635846709539,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 42,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:14Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1744.789818576751,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 63.4289408206194,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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": 43,
      "max_score": null,
      "measured_at": "2026-09-10T10:00:26Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1725.6940221336674,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 61.83347349707339,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 119,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-8-27b:739c4d774075dc83",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 4,
      "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": 54,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:13Z",
      "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": 119,
      "rating_method": "sequential_elo",
      "raw_elo": 1723.2392832402293,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 61.64418656956991,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.8935464587638418,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 204,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-sol:92a27bf667504f91",
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "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": "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": 77,
      "max_score": null,
      "measured_at": "2026-09-10T11:07:47Z",
      "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": 204,
      "rating_method": "sequential_elo",
      "raw_elo": 1712.4066257257862,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 61.45873236257106,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 154,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-5:b56db7c91f30e821",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 77,
      "draws": 15,
      "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": 37,
      "max_score": null,
      "measured_at": "2026-08-05T05:10:23Z",
      "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": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1729.9610845756647,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 61.43562510044728,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.465804565350075,
      "unilateral_faults": 0,
      "wins": 102
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-5:a77a9da79f1450e0",
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 21,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-08-05T02:28:59Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1723.735552560467,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 60.47607649312432,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 121,
      "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": 60,
      "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": 54,
      "max_score": null,
      "measured_at": "2026-09-10T11:12:08Z",
      "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": 119,
      "rating_method": "sequential_elo",
      "raw_elo": 1679.7741147045783,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 58.069604157521695,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.8935464587638418,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 184,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-5:2bf46853c4c2a3bc",
      "capped_draws": 84,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 88,
      "draws": 84,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-08-05T05:15:42Z",
      "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": 183,
      "rating_method": "sequential_elo",
      "raw_elo": 1682.921562770389,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 57.90922869975661,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.265465154150444,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 356,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-6-flash:13a24e3021af753a",
      "capped_draws": 187,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 139,
      "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": "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": 48,
      "max_score": null,
      "measured_at": "2026-09-10T04:50:55Z",
      "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": 356,
      "rating_method": "sequential_elo",
      "raw_elo": 1676.8379285851024,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 57.908198892761675,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.79454145484633,
      "unilateral_faults": 0,
      "wins": 121
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 203,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-sol:e615ab726629f0c0",
      "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": "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": 80,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:42Z",
      "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": 203,
      "rating_method": "sequential_elo",
      "raw_elo": 1665.561627843407,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 57.6005678523054,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 259,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:moonshotai-kimi-k3:6a00f2f5a49a8584",
      "capped_draws": 43,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 92,
      "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": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-09-10T01:06:50Z",
      "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": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1661.6676787014649,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 57.5234825792159,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 119,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-6-astra:9acce95ba71bd7c5",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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-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": 44,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:15Z",
      "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": 119,
      "rating_method": "sequential_elo",
      "raw_elo": 1671.1890753713847,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 57.36356914969686,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.8935464587638418,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-5-flash:79befaaad7974375",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": "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": 56,
      "max_score": null,
      "measured_at": "2026-09-10T11:08:39Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1665.395177936089,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 56.899512876213336,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-8-flash:6b8b02f1f727feff",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": "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": 49,
      "max_score": null,
      "measured_at": "2026-09-10T11:10:07Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1661.8397195918333,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 56.60711141333341,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:moonshotai-kimi-k3:ccf8a3c1c9260d55",
      "capped_draws": 29,
      "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": "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": 108,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:10Z",
      "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": 272,
      "rating_method": "sequential_elo",
      "raw_elo": 1640.1968317903131,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.82678776607858,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-5:1a25631bf54a6363",
      "capped_draws": 52,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 52,
      "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": 2,
      "max_score": null,
      "measured_at": "2026-08-05T01:23:55Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1653.6326315257897,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.17385603478494,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-7-max:a92ef5f3c3f212e3",
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 21,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-07-30T23:26:21Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1655.1143223765005,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.08434421637588,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 243,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-5:9f0371e603fb81bd",
      "capped_draws": 39,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 89,
      "draws": 39,
      "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": 80,
      "max_score": null,
      "measured_at": "2026-09-10T11:05:01Z",
      "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": 243,
      "rating_method": "sequential_elo",
      "raw_elo": 1625.9511140533318,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.54022332767149,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-4-mini:e296afd987da0af3",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "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-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": 22,
      "max_score": null,
      "measured_at": "2026-08-03T16:16:35Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1642.0222732482737,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.00765200217118,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 2,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-4-1:731bd482a4919a05",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "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-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": 31,
      "max_score": null,
      "measured_at": "2026-08-05T04:19:05Z",
      "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": 81,
      "rating_method": "sequential_elo",
      "raw_elo": 1635.2135372709856,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.77515864460839,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.465763037423269,
      "unilateral_faults": 1,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:x-ai-grok-4-6:bca3abc3bf41095f",
      "capped_draws": 33,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "draws": 33,
      "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": 59,
      "max_score": null,
      "measured_at": "2026-09-10T11:09:42Z",
      "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": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1621.1494007222223,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.57424063188693,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 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": 57,
      "max_score": null,
      "measured_at": "2026-09-10T11:10:23Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1621.4320540516248,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.28397853663737,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": null,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-8:95b343605f7f7184",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 13,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-08-04T21:47:36Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1628.124836644718,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 52.97475225210645,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 39
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-5:a953aed661ace78d",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 45,
      "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",
        "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": 37,
      "max_score": null,
      "measured_at": "2026-08-03T14:42:13Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1632.891716608698,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 52.610603965911444,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.264004201400486,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-fable-5:346aadd5d76b812b",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 15,
      "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": 56,
      "max_score": null,
      "measured_at": "2026-09-10T11:07:47Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1602.7025644270188,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 51.74366231437673,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 210,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:meta-muse-spark-1-2:c4024993f2e98d89",
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "draws": 22,
      "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": 101,
      "max_score": null,
      "measured_at": "2026-09-10T11:05:40Z",
      "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": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1593.052861841246,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 51.675962062161574,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-fable-5:1f4ca1763387a608",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 15,
      "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": 54,
      "max_score": null,
      "measured_at": "2026-09-10T11:07:59Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1601.767086979764,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 51.666728499497296,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:z-ai-glm-5-3-flash:6bc93e3f26e0f0e5",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": "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": 58,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:10Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1596.763908226237,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 51.25526627861526,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:x-ai-grok-4-6:d94ddefd8b9f53eb",
      "capped_draws": 42,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 42,
      "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": 35,
      "max_score": null,
      "measured_at": "2026-09-10T11:09:42Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1595.6553927632428,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 51.1641017896463,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:78fb6a9e00356b09",
      "capped_draws": 41,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 41,
      "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": 61,
      "max_score": null,
      "measured_at": "2026-09-10T01:49:09Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1585.9593303575618,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.52600493863421,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-8:c5e685ce6c400bea",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 17,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-07-31T01:07:22Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1600.772685219599,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.49524544599616,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:tencent-hy3-preview:173ea133649c5bcd",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "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": "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": 23,
      "max_score": null,
      "measured_at": "2026-08-03T13:20:55Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1594.4036920144524,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.032819133002,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:z-ai-glm-5-3-flash:1540ade2fda6b881",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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-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": 63,
      "max_score": null,
      "measured_at": "2026-09-10T11:05:40Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1579.1908972997724,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.834472121274,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 298,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-5:e2ff6744eb1bb7c6",
      "capped_draws": 84,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 84,
      "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": 99,
      "max_score": null,
      "measured_at": "2026-09-10T11:09:47Z",
      "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": 298,
      "rating_method": "sequential_elo",
      "raw_elo": 1562.931340214569,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.56099324474412,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 156,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-4-nano:8753e840d1cee063",
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 76,
      "draws": 49,
      "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": 45,
      "max_score": null,
      "measured_at": "2026-08-05T05:01:18Z",
      "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": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1580.3713321653136,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.18855338448374,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.626594026364666,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:z-ai-glm-5-3:9e30a36ab00bd740",
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 21,
      "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": 60,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:19Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.9304941065209,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.63728121007812,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:stealth-ox-alpha:6719f8157bcde29f",
      "capped_draws": 64,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 142,
      "draws": 64,
      "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": 114,
      "max_score": null,
      "measured_at": "2026-09-10T11:12:08Z",
      "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": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 1557.5471242852395,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.22093354536652,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 100
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 164,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:tencent-hy4-preview:2077a0aa15ce66b2",
      "capped_draws": 71,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "draws": 71,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-09-10T11:05:01Z",
      "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": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1553.627998089601,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.137358293252255,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-terra:bd3aacb7be18fc49",
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 24,
      "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": 43,
      "max_score": null,
      "measured_at": "2026-09-10T04:47:49Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1555.767687387719,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.93196838089745,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 380,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:stealth-ox-alpha:fe3b437dca2c4367",
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 190,
      "draws": 21,
      "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": 176,
      "max_score": null,
      "measured_at": "2026-09-10T11:09:55Z",
      "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": 380,
      "rating_method": "sequential_elo",
      "raw_elo": 1554.229696147544,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.83064684889641,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.1363636363636391,
      "unilateral_faults": 0,
      "wins": 183
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 740,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:o3:1084c60ee563e860",
      "capped_draws": 78,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 260,
      "draws": 78,
      "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": 298,
      "max_score": null,
      "measured_at": "2026-09-10T11:09:51Z",
      "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": 740,
      "rating_method": "sequential_elo",
      "raw_elo": 1542.8030567183832,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.71717706185117,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 364
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemma-4-31b-it:e2b2f6f0f78a1f3f",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "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": "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": 30,
      "max_score": null,
      "measured_at": "2026-08-05T03:13:53Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1555.8128707841634,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.537908439761935,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:x-ai-grok-4-6:aedb1b245d3cd53f",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "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": "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": 67,
      "max_score": null,
      "measured_at": "2026-09-10T04:07:50Z",
      "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": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1544.2101064830151,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.0047308381856,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 142,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-8-flash:83795e08736dcbd6",
      "capped_draws": 52,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 71,
      "draws": 52,
      "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": 61,
      "max_score": null,
      "measured_at": "2026-09-10T03:21:48Z",
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.7506367849912,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.88837008118324,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5:16f7def69ce10ccd",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 5,
      "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": 40,
      "max_score": null,
      "measured_at": "2026-08-03T12:31:39Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.0545313969262,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.42515101914064,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:be72f75fe8d3007b",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 12,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-07-31T03:24:08Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1551.903907212254,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.34461449749834,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:minimax-minimax-m3:6639861dd7b73e51",
      "capped_draws": 20,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "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": "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": 32,
      "max_score": null,
      "measured_at": "2026-08-05T03:20:28Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.7263032874123,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.149209979529324,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 146,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:tencent-hy4-preview:014a9ceb67d5b786",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "draws": 10,
      "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": 86,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:19Z",
      "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": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.6533895280302,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.013416130569944,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-pro:c37d073d6b142a09",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "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-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": 83,
      "max_score": null,
      "measured_at": "2026-09-10T09:51:03Z",
      "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": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.056868577737,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.836055739473956,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 152,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-8-flash:e50b23a03b02a00c",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 76,
      "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": "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": 89,
      "max_score": null,
      "measured_at": "2026-09-10T07:16:36Z",
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1524.210378608972,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.61951452356562,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:xiaomi-mimo-v2-5:35035a0b78826dbc",
      "capped_draws": 22,
      "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": "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": 40,
      "max_score": null,
      "measured_at": "2026-08-05T01:58:44Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1530.6157011755522,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.49959959489141,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 340,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:x-ai-grok-4-5:365663c1de2ba20d",
      "capped_draws": 200,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 123,
      "draws": 200,
      "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": 90,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:37Z",
      "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": 340,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.9079406908675,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.3213471472622,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 164,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:z-ai-glm-5-2:20c65e2b7513d4b4",
      "capped_draws": 55,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "draws": 55,
      "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": 68,
      "max_score": null,
      "measured_at": "2026-09-10T11:05:49Z",
      "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": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.440886827866,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.243564635376174,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-sonnet-5:ec6362fd3d2a0220",
      "capped_draws": 28,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 91,
      "draws": 28,
      "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": 108,
      "max_score": null,
      "measured_at": "2026-09-10T07:39:14Z",
      "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": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1506.4520159219408,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.70826959385252,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 174,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:z-ai-glm-5-3:2dbca3140c06e14c",
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 87,
      "draws": 26,
      "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": 81,
      "max_score": null,
      "measured_at": "2026-09-10T11:09:42Z",
      "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": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.5022233610664,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.58269393252839,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 339,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:moonshotai-kimi-k3:f0bfe8c58b2cc988",
      "capped_draws": 198,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 121,
      "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": "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": 85,
      "max_score": null,
      "measured_at": "2026-09-10T10:00:57Z",
      "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": 339,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.2302043286434,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.276110266794404,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:o3:f70fd8105d3dfec2",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "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": "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": 30,
      "max_score": null,
      "measured_at": "2026-08-03T14:22:08Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.7878014821274,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.26017199969047,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 34
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 144,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:xiaomi-mimo-v2-5:235a446f3a9f9cd3",
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 72,
      "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": "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": 60,
      "max_score": null,
      "measured_at": "2026-07-31T03:00:46Z",
      "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": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.1853582483902,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.24477927924515,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.036461425079892,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-5:53d4c02c8a9496db",
      "capped_draws": 76,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 76,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-08-05T05:09:23Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.9554170592792,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.211695324514714,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 517,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-6-flash:b4583ef7c04d45cd",
      "capped_draws": 174,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 187,
      "draws": 174,
      "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": 179,
      "max_score": null,
      "measured_at": "2026-09-10T11:10:23Z",
      "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": 514,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.2581565241724,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.1763070086701,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 161
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:moonshotai-kimi-k2-7-code:0eac35852db14de0",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "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": "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": 37,
      "max_score": null,
      "measured_at": "2026-08-05T01:23:03Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1515.2417696657326,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.01459558203363,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 45
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 192,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:poolside-laguna-s-2-1:533b6103a5973424",
      "capped_draws": 43,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 92,
      "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": "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": 78,
      "max_score": null,
      "measured_at": "2026-08-05T05:02:20Z",
      "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": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.9064973950458,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.92223550931248,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.090352872155288,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 155,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:b4ca94f8b60a9e88",
      "capped_draws": 50,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 78,
      "draws": 50,
      "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": 38,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:56Z",
      "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": 155,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.4989415222879,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.44845781533551,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:x-ai-grok-build-0-1:55f4f20890a40d69",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 17,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-08-04T20:42:26Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.378396323981,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.119446315546206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-8:8ccf8977401d94db",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 15,
      "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": 26,
      "max_score": null,
      "measured_at": "2026-08-03T14:21:46Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.3231224366134,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.09168274262431,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 144,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:tencent-hy4-preview:b8e7119f660161ad",
      "capped_draws": 30,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "draws": 30,
      "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": 46,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:38Z",
      "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": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.93570480965,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.97510007604222,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 165,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-8-flash:98dfb2fac355b676",
      "capped_draws": 65,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 83,
      "draws": 65,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:42Z",
      "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": 165,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.517249176712,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.79036526143108,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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:GB2-01:publication-row.v1:mixed:qwen-qwen3-7-plus:e4e482b5c34e690f",
      "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": "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": 32,
      "max_score": null,
      "measured_at": "2026-08-03T09:57:34Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.5386153907175,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.34815521713447,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:z-ai-glm-5-2:f14efcbac580ffaa",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 7,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-07-31T01:08:24Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.9322821822525,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.91094761181159,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-1-flash-lite:4c9cdde1729642af",
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "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": "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": 25,
      "max_score": null,
      "measured_at": "2026-08-05T02:21:14Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.886972534093,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.80592199500637,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:a3e60c7aa64704be",
      "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": "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": 27,
      "max_score": null,
      "measured_at": "2026-08-03T02:39:09Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.0591958988462,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.78469219527432,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 155,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-terra:4506b3e0a8fb5629",
      "capped_draws": 60,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 78,
      "draws": 60,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-09-10T11:12:01Z",
      "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": 155,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.2113320692047,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.780001569180335,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 168,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:d3192451477fbf98",
      "capped_draws": 117,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "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": "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": 18,
      "max_score": null,
      "measured_at": "2026-09-10T11:10:07Z",
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.6924784481903,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.51169686092654,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 241,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-luna:29e28a5adce9180a",
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 92,
      "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": "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": 93,
      "max_score": null,
      "measured_at": "2026-09-10T11:05:04Z",
      "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": 241,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.15171118097,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.4718506514852,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 166,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-flash:14b865d3f352c468",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "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-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": 93,
      "max_score": null,
      "measured_at": "2026-09-10T07:19:38Z",
      "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": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.762226451547,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 40.9935033407125,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 146,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:openai-gpt-oss-120b:07d17099885c6bdb",
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "draws": 29,
      "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": 51,
      "max_score": null,
      "measured_at": "2026-09-10T07:20:06Z",
      "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": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.316176854037,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 40.640073310441565,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-sonnet-5:a86621e2793b5dec",
      "capped_draws": 41,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "draws": 41,
      "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": 97,
      "max_score": null,
      "measured_at": "2026-09-10T06:33:43Z",
      "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": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.585426437345,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 40.38863436219846,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 282,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:poolside-laguna-s-2-1:07eac22bdea1b9b3",
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "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": "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": 116,
      "max_score": null,
      "measured_at": "2026-09-10T09:58:35Z",
      "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": 282,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.3853679490633,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 40.16991479649198,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 616,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-5-flash-lite:0bab1c3ea19c7cb7",
      "capped_draws": 120,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 220,
      "draws": 120,
      "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": 237,
      "max_score": null,
      "measured_at": "2026-09-10T09:53:51Z",
      "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": 616,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.1140497986676,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.89414504066892,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 136,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:openai-gpt-oss-120b:59563b7e90e4a253",
      "capped_draws": 34,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 68,
      "draws": 34,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-09-10T06:22:35Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.0391376524533,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 38.95744773414053,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-5:959db58a0f4d59b9",
      "capped_draws": 62,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "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-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": 20,
      "max_score": null,
      "measured_at": "2026-08-05T05:02:30Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.0431859406906,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 38.72217677162721,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:xiaomi-mimo-v2-5:32918e3c3e0fca83",
      "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": "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": 38,
      "max_score": null,
      "measured_at": "2026-07-31T02:06:06Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.0620455775036,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 38.36143436251241,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 221,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-sonnet-5:73f1b29a5c45562d",
      "capped_draws": 50,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "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-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": 74,
      "max_score": null,
      "measured_at": "2026-09-10T05:36:36Z",
      "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": 221,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.215755307793,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 38.09431108312192,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 134,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-8-max:644816d2bc8a5f5c",
      "capped_draws": 62,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "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": "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": 34,
      "max_score": null,
      "measured_at": "2026-09-10T11:05:43Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.6091705822635,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.585502632645984,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 130,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-5-flash:e1e7937be001cd2a",
      "capped_draws": 36,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 65,
      "draws": 36,
      "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": 37,
      "max_score": null,
      "measured_at": "2026-09-10T04:54:04Z",
      "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": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.3260253195192,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.2725961852945,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 152,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:bytedance-seed-seed-2-0-code:2447db730c8d12fe",
      "capped_draws": 28,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 76,
      "draws": 28,
      "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": 56,
      "max_score": null,
      "measured_at": "2026-09-10T09:45:46Z",
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.2377140826875,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.15102612381427,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 264,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:inclusionai-ling-3-0-flash:1ed2a890413ad375",
      "capped_draws": 83,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 98,
      "draws": 83,
      "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": 97,
      "max_score": null,
      "measured_at": "2026-08-05T05:09:16Z",
      "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": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.3866478960922,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.1347934270453,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:meta-muse-glimmer-30b:a614a905445f79d1",
      "capped_draws": 43,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "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": "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": 40,
      "max_score": null,
      "measured_at": "2026-09-10T04:12:37Z",
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.3375622947487,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.00463002835304,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:36d8ebdcb946256c",
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 26,
      "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": 45,
      "max_score": null,
      "measured_at": "2026-08-05T04:19:05Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.1690382660745,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 36.13581747923515,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:z-ai-glm-5-3-flash:22cd36959459fbdd",
      "capped_draws": 86,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 68,
      "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": "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": 31,
      "max_score": null,
      "measured_at": "2026-09-10T04:07:20Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.9308922376556,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.9878998561934,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-flash:dac448fbfe2a5737",
      "capped_draws": 30,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 55,
      "draws": 30,
      "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": 51,
      "max_score": null,
      "measured_at": "2026-07-31T02:19:27Z",
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.0009132132132,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.6157851053112,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.461325131721317,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 573,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-5-flash-lite:55634764b9427e4e",
      "capped_draws": 133,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 206,
      "draws": 133,
      "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": 239,
      "max_score": null,
      "measured_at": "2026-09-10T11:12:00Z",
      "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": 573,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.6675927319038,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.52053358030793,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-4-mini:9285646640165917",
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 35,
      "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": 34,
      "max_score": null,
      "measured_at": "2026-08-05T05:15:42Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.332536316064,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.304603292582,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-4-1-nano:68d5f0be3c90fb50",
      "capped_draws": 65,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 65,
      "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": 103,
      "max_score": null,
      "measured_at": "2026-09-10T04:08:50Z",
      "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": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 1388.89236890581,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.18099307381629,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:94c7956182cf2d89",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "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": "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": 32,
      "max_score": null,
      "measured_at": "2026-08-05T03:16:49Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.5929703577895,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.81038879854182,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 17
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 400,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:stealth-ox-alpha:dfb3dd7361cfa1a2",
      "capped_draws": 120,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 200,
      "draws": 120,
      "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": 154,
      "max_score": null,
      "measured_at": "2026-09-10T10:10:04Z",
      "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": 400,
      "rating_method": "sequential_elo",
      "raw_elo": 1394.9933919244042,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.80493220290756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.5681818181818196,
      "unilateral_faults": 0,
      "wins": 126
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:d0b5b92265541548",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 4,
      "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": 48,
      "max_score": null,
      "measured_at": "2026-09-10T11:05:43Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1388.3076463525476,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.13620303413409,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 210,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:meituan-longcat-2-0:45102822fc5f9296",
      "capped_draws": 71,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 99,
      "draws": 71,
      "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": 80,
      "max_score": null,
      "measured_at": "2026-08-05T05:02:36Z",
      "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": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1390.4482752690915,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.08227841090624,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.828889084636114,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-8-flash:e1a2822fb5bba20e",
      "capped_draws": 43,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": "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": 37,
      "max_score": null,
      "measured_at": "2026-09-10T11:08:14Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1386.0107501750101,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.92289285331455,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": null,
      "draws": 74,
      "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": 35,
      "max_score": null,
      "measured_at": "2026-07-31T03:28:47Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1395.5581331701767,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.679728570943254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": null,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-5-flash-lite:5943a501fa6113ab",
      "capped_draws": 57,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 83,
      "draws": 57,
      "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": 116,
      "max_score": null,
      "measured_at": "2026-09-10T11:08:35Z",
      "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": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1368.4377311620217,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.35795274164543,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 144,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:z-ai-glm-5-2:4571486d5f3c5826",
      "capped_draws": 103,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 72,
      "draws": 103,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-09-10T03:17:54Z",
      "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": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1367.3220589752111,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.64461375238407,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:bytedance-seed-seed-2-0-code:c69120230888411c",
      "capped_draws": 73,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 73,
      "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": 25,
      "max_score": null,
      "measured_at": "2026-09-10T11:08:48Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1364.7121364177256,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.19570452330597,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:z-ai-glm-5-2:5ea14bc9644b6a2b",
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 61,
      "draws": 21,
      "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": 55,
      "max_score": null,
      "measured_at": "2026-07-31T02:21:34Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1378.4214415080905,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.10781951088912,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.805911392508083,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-pro:c11fecb63644464d",
      "capped_draws": 46,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": "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": 53,
      "max_score": null,
      "measured_at": "2026-09-10T11:09:42Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1356.9101246436917,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.55406582718129,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 202,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:meta-muse-spark-1-2:539f99e7c4c4b6ea",
      "capped_draws": 98,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "draws": 98,
      "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": 68,
      "max_score": null,
      "measured_at": "2026-09-10T11:08:49Z",
      "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": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 1346.9862893086279,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.395215158594592,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-7-plus:cdc5232f1e60910a",
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 22,
      "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": 43,
      "max_score": null,
      "measured_at": "2026-08-04T23:49:57Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1360.7360649255008,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.224037847715838,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:minimax-minimax-m3:6f48906184a5bdb8",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "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": "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": 49,
      "max_score": null,
      "measured_at": "2026-08-05T02:21:31Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1350.9691174196694,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.37649642208813,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:45ec16f47504b5f5",
      "capped_draws": 34,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 34,
      "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": 50,
      "max_score": null,
      "measured_at": "2026-09-10T11:09:23Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1335.8049891606988,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.818376109573915,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:meta-muse-glimmer-30b:085624a1bd2a3883",
      "capped_draws": 54,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 54,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-09-10T11:07:30Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1331.2121180284705,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.440657653090735,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:xiaomi-mimo-v2-5:3449c1aec50b70b2",
      "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-v2.5",
        "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": 43,
      "max_score": null,
      "measured_at": "2026-08-05T01:23:13Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1333.1371652243768,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.03828378756427,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:thinkingmachines-inkling:b27963da4b6944f2",
      "capped_draws": 76,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 90,
      "draws": 76,
      "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": 120,
      "max_score": null,
      "measured_at": "2026-09-10T09:56:33Z",
      "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": 1301.8495200374323,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.89888466985854,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:z-ai-glm-5-2:184634950256ca6a",
      "capped_draws": 48,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "draws": 48,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-09-10T09:56:11Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1304.7434331607394,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.214429734485332,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:meta-muse-glimmer-30b:20d2aea9e268d0ef",
      "capped_draws": 48,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 48,
      "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": 54,
      "max_score": null,
      "measured_at": "2026-09-10T09:57:21Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1303.0183569125913,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.097585157882463,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 553,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-6-flash:b574aaabaed70f28",
      "capped_draws": 147,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 199,
      "draws": 147,
      "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": 272,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:14Z",
      "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": 553,
      "rating_method": "sequential_elo",
      "raw_elo": 1282.3886606251967,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.416793040873507,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 182,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:cohere-north-mini-code:4a23759df70ab26b",
      "capped_draws": 84,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 84,
      "draws": 84,
      "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": 80,
      "max_score": null,
      "measured_at": "2026-08-05T05:09:16Z",
      "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": 182,
      "rating_method": "sequential_elo",
      "raw_elo": 1297.9536523160737,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.207095835838984,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.908556341051073,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:thinkingmachines-inkling-small:c4a079d6b58a2c73",
      "capped_draws": 46,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 46,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-09-10T09:59:45Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1290.1434413527058,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.03875004306578,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5:3bb27dbc092c7ff2",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "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-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": 40,
      "max_score": null,
      "measured_at": "2026-08-05T04:11:21Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1292.4869742782632,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.31798930091367,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 121,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-8-27b:47ad2584aeb815bb",
      "capped_draws": 74,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 74,
      "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": 30,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:56Z",
      "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": 121,
      "rating_method": "sequential_elo",
      "raw_elo": 1280.5318378187312,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.260571807798776,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.5178730212592662,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:f9ec308f9bb8850b",
      "capped_draws": 67,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 67,
      "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": 39,
      "max_score": null,
      "measured_at": "2026-09-10T09:56:53Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1279.1252646960281,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.13261343260962,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "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": 70,
      "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": 167,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:55Z",
      "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": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1277.318453124216,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.818807678882663,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:xiaomi-mimo-v2-5:024b37c390436d5a",
      "capped_draws": 39,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "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": "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": 19,
      "max_score": null,
      "measured_at": "2026-07-31T00:39:03Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1277.5373789071825,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.780667328407972,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 121,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-pro:42034002bcfc5f74",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 7,
      "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": 81,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:38Z",
      "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": 121,
      "rating_method": "sequential_elo",
      "raw_elo": 1262.4843318048977,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.77634202676228,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.5178730212592662,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 121,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-8-max:7b21229bd01e0b5e",
      "capped_draws": 32,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 32,
      "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": 60,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:37Z",
      "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": 121,
      "rating_method": "sequential_elo",
      "raw_elo": 1261.9654836736365,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.733671873464495,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.5178730212592662,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-7-max:fa240f0afd3eda59",
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 24,
      "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": 38,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:20Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1267.5817664088527,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.323632491834545,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:inception-mercury-2-5-preview:ff9c957a999941a2",
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": "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": 63,
      "max_score": null,
      "measured_at": "2026-09-10T09:58:35Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1257.0243633029106,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.315031767294062,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 144,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-4-nano:4caf0453cfb54e62",
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 69,
      "draws": 26,
      "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": 88,
      "max_score": null,
      "measured_at": "2026-08-05T03:22:02Z",
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1258.698860860387,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.50128480022854,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.166122297570965,
      "unilateral_faults": 2,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 121,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:meta-muse-spark-1-3:22ddc49b675eb171",
      "capped_draws": 45,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 45,
      "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": 56,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:12Z",
      "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": 121,
      "rating_method": "sequential_elo",
      "raw_elo": 1224.6314436184432,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.663314448241664,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.5178730212592662,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:thinkingmachines-inkling-small:f1451a0a6af20650",
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "draws": 29,
      "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": 76,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:12Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1217.2337078268613,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.22269275083169,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 202,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-luna:15a0f0a09f9eb8e5",
      "capped_draws": 50,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "draws": 50,
      "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": 125,
      "max_score": null,
      "measured_at": "2026-09-10T10:02:20Z",
      "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": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 1197.0126079825945,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 19.061355620043653,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 198,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:thinkingmachines-inkling:a1a9848a1d14b67e",
      "capped_draws": 71,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 93,
      "draws": 71,
      "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": 107,
      "max_score": null,
      "measured_at": "2026-08-05T05:09:23Z",
      "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": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1208.8856537756806,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 19.0569181003493,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.251875136730032,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:stepfun-step-3-7-flash:0e0f63cf65826515",
      "capped_draws": 6,
      "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": "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": 43,
      "max_score": null,
      "measured_at": "2026-08-05T02:35:13Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1204.0077738517675,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.73358084856714,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-8-max:a791831295f0ee80",
      "capped_draws": 40,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 40,
      "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": 78,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:21Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1180.193855108586,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.134579252744338,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-1-flash-lite:f12274812b7e4c60",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "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": "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": 37,
      "max_score": null,
      "measured_at": "2026-07-31T03:26:44Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1195.0228351994263,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.062052955412074,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-flash:04d7da5a4f2e2af2",
      "capped_draws": 38,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 38,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:10Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1179.7962359680705,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 16.963778223663805,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-flash:e0a2978fff9e81b1",
      "capped_draws": 39,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 39,
      "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": 76,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:36Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1176.5212783168986,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 16.69444518264546,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:bytedance-seed-seed-2-0-code:e037862ab5c7ecb3",
      "capped_draws": 40,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 40,
      "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": 74,
      "max_score": null,
      "measured_at": "2026-09-10T10:05:22Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1163.7794884300404,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 15.646558344470218,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:thinkingmachines-inkling:281eafa14f6ff011",
      "capped_draws": 95,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 83,
      "draws": 95,
      "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": 139,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:12Z",
      "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": 1148.0712009628478,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 15.234974053366383,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:o3:29970c6bc7db3c37",
      "capped_draws": 81,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 96,
      "draws": 81,
      "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": 172,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:32Z",
      "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": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1127.6524674454595,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 13.652811210043236,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 136,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:thinkingmachines-inkling-small:6603774c29b8a046",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": "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": 114,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:00Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 971.3356846908011,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 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": 5,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:04Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1947.6719384807805,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": null,
      "wins": 94
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 5,
      "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": "2026-09-10T10:26:15Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1941.5395346701005,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 98.89567905132267,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 96
    },
    {
      "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": 14,
      "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": 7,
      "max_score": null,
      "measured_at": "2026-09-10T10:09:03Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1834.7977187233885,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 79.6736533842389,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": null,
      "wins": 83
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 168,
      "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": 72,
      "draws": 47,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:37Z",
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1775.3612754351213,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 70.45903844353168,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 104,
      "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": 52,
      "draws": 36,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:00Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1782.338822767404,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 70.22687532833427,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 60
    },
    {
      "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": 38,
      "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": "2026-09-10T10:05:37Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1776.8781358681929,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 69.24351690590547,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": null,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 22,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:30Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1750.965809215415,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 64.57723496573112,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "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": "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": 12,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:45Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1731.8618926517001,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 61.13700892804711,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "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": 22,
      "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-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": 1,
      "max_score": null,
      "measured_at": "2026-08-03T08:04:24Z",
      "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": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1729.7796436772644,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 57.70515067638105,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.264004201400486,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 208,
      "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": 104,
      "draws": 82,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:17Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1701.0026010053057,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.57987941105307,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 104,
      "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": 52,
      "draws": 58,
      "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": 14,
      "max_score": null,
      "measured_at": "2026-09-10T10:00:08Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1684.8593509221103,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 52.67280906849635,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 46,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-09-10T10:00:00Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1672.6595864434637,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.47588011557324,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 47
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 120,
      "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": 60,
      "draws": 45,
      "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": 7,
      "max_score": null,
      "measured_at": "2026-08-05T04:33:25Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1665.9022944138023,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.062164269002736,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.294267162641567,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 36,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-09-10T09:57:30Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1647.3925469912467,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.92580124934712,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 52
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 100,
      "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": 50,
      "draws": 38,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-03T12:23:36Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1661.2356908966067,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.36178169780819,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.264004201400486,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 66,
      "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": 27,
      "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": "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": 11,
      "max_score": null,
      "measured_at": "2026-08-04T08:44:46Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1655.3294738631357,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.027298685176675,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 42.0271267253503,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 168,
      "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": 70,
      "draws": 94,
      "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": 18,
      "max_score": null,
      "measured_at": "2026-09-10T09:57:15Z",
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1600.6853646986274,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.00346679320183,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 104,
      "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": 52,
      "draws": 47,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-09-10T09:57:20Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1591.2257260959202,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.81130147891559,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:z-ai-glm-5-3:650c1432bdd4728a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 61,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-09-10T09:57:09Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1589.3898232530091,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.48069279237866,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "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": 83,
      "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": "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": 46,
      "max_score": null,
      "measured_at": "2026-09-10T09:53:50Z",
      "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": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1576.638708912993,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.41194233918621,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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:GB2-02: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": 52,
      "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": "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": 18,
      "max_score": null,
      "measured_at": "2026-09-10T09:54:19Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1569.6854300230325,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.93233314474059,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "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": 24,
      "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-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": 5,
      "max_score": null,
      "measured_at": "2026-08-03T09:39:04Z",
      "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": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1580.7065130209066,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.656330153885765,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.678571428571434,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "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/qwen3.8-2.4t-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": 22,
      "max_score": null,
      "measured_at": "2026-09-10T09:52:39Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1555.0517257485558,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.297101237978474,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "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": "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": 20,
      "max_score": null,
      "measured_at": "2026-09-10T09:52:37Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1553.8558854814169,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.081754776942507,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 61,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-09-10T09:53:31Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.1931602057512,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.901057918937127,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:z-ai-glm-5-3:2dbca3140c06e14c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 71,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-09-10T09:49:55Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.8916581476587,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.766285822102056,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "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": "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": 23,
      "max_score": null,
      "measured_at": "2026-09-10T09:51:01Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1526.4996754354536,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.155458863819263,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 60,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-09-10T09:50:54Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1517.647170216129,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.56130308677311,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 113,
      "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": 53,
      "draws": 82,
      "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": 19,
      "max_score": null,
      "measured_at": "2026-09-10T09:50:56Z",
      "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": 113,
      "rating_method": "sequential_elo",
      "raw_elo": 1515.1242452926706,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.390163615050678,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.079290579084697,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 58,
      "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": 29,
      "max_score": null,
      "measured_at": "2026-09-10T09:50:33Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.8092095628847,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 21.32992572991054,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 52,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-09-10T09:49:06Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.2607155527892,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.87099389668296,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 69,
      "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": 28,
      "max_score": null,
      "measured_at": "2026-09-10T06:12:59Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.65479163134,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 18.420844285465474,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "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": "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": 21,
      "max_score": null,
      "measured_at": "2026-09-10T09:49:12Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.3429910044993,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 18.364695347029407,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "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": 29,
      "draws": 45,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-08-04T20:03:05Z",
      "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": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.3189852487574,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.63292970387716,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 8
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 372,
      "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": 186,
      "draws": 280,
      "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": 55,
      "max_score": null,
      "measured_at": "2026-09-10T09:53:16Z",
      "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": 372,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.8477800060446,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 16.948694007756043,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.3633357649511098,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "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": 35,
      "draws": 58,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-04T21:44:58Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.6675869461267,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 16.904129430402378,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 64,
      "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": 29,
      "draws": 53,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-03T04:42:24Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.5372685658526,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 16.49481819829116,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "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": 29,
      "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": "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": 5,
      "max_score": null,
      "measured_at": "2026-08-03T08:48:42Z",
      "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": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.8783062336413,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 16.473094673491183,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 42,
      "draws": 75,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-08-03T14:15:10Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.9471496450988,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 15.971215353629413,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "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": 33,
      "draws": 66,
      "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": 1,
      "max_score": null,
      "measured_at": "2026-08-03T12:16:41Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.9829898555085,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 15.520290105513986,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 215,
      "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": 85,
      "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": "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": 40,
      "max_score": null,
      "measured_at": "2026-09-10T07:39:30Z",
      "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": 215,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.9244064409238,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 15.37552954010579,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 64,
      "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": 30,
      "draws": 58,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-08-03T09:30:46Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.71508709671,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 15.266282350907517,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "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": 29,
      "draws": 59,
      "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": 2,
      "max_score": null,
      "measured_at": "2026-08-03T14:15:15Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.1517568183824,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 15.204208993992154,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "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": 28,
      "draws": 54,
      "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": 1,
      "max_score": null,
      "measured_at": "2026-08-05T02:59:59Z",
      "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": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.1858427728368,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 15.08783877564788,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "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": 36,
      "draws": 52,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-08-02T23:10:13Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.9101853302607,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 15.084858110615464,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:xiaomi-mimo-v2-5:024b37c390436d5a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "draws": 40,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-07-31T01:21:08Z",
      "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": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.949735935574,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 14.876831236011256,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.264004201400486,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "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": 25,
      "draws": 48,
      "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": 1,
      "max_score": null,
      "measured_at": "2026-07-31T03:32:23Z",
      "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": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.7142636458952,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 14.474268235287061,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.264004201400486,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "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": 36,
      "draws": 74,
      "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": 0,
      "max_score": null,
      "measured_at": "2026-08-05T02:59:50Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.2664311879878,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 14.181701766649182,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "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": 32,
      "draws": 58,
      "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": 6,
      "max_score": null,
      "measured_at": "2026-08-04T23:05:09Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.3280306730896,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 13.936024036303673,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 124,
      "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": 58,
      "draws": 116,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-07-30T20:06:29Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.949173525208,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 13.893411007112569,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.339588834282274,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": null,
      "draws": 90,
      "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": 4,
      "max_score": null,
      "measured_at": "2026-07-31T03:32:27Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.7153412970197,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 13.80218482679183,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 28.430533588759353,
      "unilateral_faults": null,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "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": 99,
      "draws": 230,
      "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": 26,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:45Z",
      "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": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.9009704052921,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 13.63565896036477,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 146,
      "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": 73,
      "draws": 105,
      "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": 32,
      "max_score": null,
      "measured_at": "2026-09-10T09:49:06Z",
      "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": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.001763083591,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 13.629201190774216,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 176,
      "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": 71,
      "draws": 164,
      "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": 6,
      "max_score": null,
      "measured_at": "2026-09-10T07:14:14Z",
      "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": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.1315122058427,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 13.459089329828975,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 230,
      "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": 90,
      "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": "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": 35,
      "max_score": null,
      "measured_at": "2026-09-10T09:49:12Z",
      "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": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.2925767129848,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 13.442672880681176,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 202,
      "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": 77,
      "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": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-09-10T09:57:20Z",
      "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": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.101689505752,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 13.272080636024716,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 152,
      "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": 70,
      "draws": 122,
      "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": 28,
      "max_score": null,
      "measured_at": "2026-09-10T07:14:17Z",
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.8391048767317,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.997248213621113,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 60,
      "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": 28,
      "draws": 59,
      "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": 1,
      "max_score": null,
      "measured_at": "2026-08-03T14:15:35Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.4584951256152,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.950917619586493,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "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": 67,
      "draws": 105,
      "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": 26,
      "max_score": null,
      "measured_at": "2026-09-10T04:40:04Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.4605593091374,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.913154477319852,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 70,
      "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": 34,
      "draws": 61,
      "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": 6,
      "max_score": null,
      "measured_at": "2026-08-03T03:19:01Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.4077462615205,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.895585775886488,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": "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": 31,
      "max_score": null,
      "measured_at": "2026-09-10T07:15:09Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.2230129143188,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.807246879163486,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "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": 27,
      "draws": 43,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-08-03T08:04:56Z",
      "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": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.764023922726,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.515897799774466,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "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": 29,
      "draws": 59,
      "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": 1,
      "max_score": null,
      "measured_at": "2026-08-04T22:55:23Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.5016442990093,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.418449045966476,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 206,
      "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": 74,
      "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": "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": 24,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:30Z",
      "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": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.7760281162512,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.3621226468018,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 64,
      "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": 31,
      "draws": 62,
      "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": 1,
      "max_score": null,
      "measured_at": "2026-08-03T12:16:24Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.4473944599374,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.336802440575292,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "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": 36,
      "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": "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": 7,
      "max_score": null,
      "measured_at": "2026-08-05T04:33:30Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.0193405271866,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.336409573070739,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "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": 31,
      "draws": 55,
      "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": 7,
      "max_score": null,
      "measured_at": "2026-08-05T04:32:40Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.9810619922746,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.252825466946847,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 182,
      "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": 67,
      "draws": 171,
      "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": 6,
      "max_score": null,
      "measured_at": "2026-09-10T09:49:03Z",
      "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": 182,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.6916419866793,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.208818148161988,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 54,
      "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": 26,
      "draws": 52,
      "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": 2,
      "max_score": null,
      "measured_at": "2026-08-05T04:33:21Z",
      "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": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.9568968469735,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.190471042456242,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 132,
      "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": 66,
      "draws": 121,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-08-05T04:33:25Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.8925253457724,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.179369637744257,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.416580872281934,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 160,
      "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": 80,
      "draws": 131,
      "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": 28,
      "max_score": null,
      "measured_at": "2026-09-10T07:15:16Z",
      "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": 1452.0639490111673,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.10378519941586,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 100,
      "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": 50,
      "draws": 96,
      "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": 3,
      "max_score": null,
      "measured_at": "2026-07-31T03:30:54Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.5267053672487,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.099457750098598,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.264004201400486,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 492,
      "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": 174,
      "draws": 446,
      "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": 45,
      "max_score": null,
      "measured_at": "2026-09-10T06:13:02Z",
      "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": 492,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.952322485975,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.080494482193536,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 219,
      "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": 74,
      "draws": 215,
      "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": 4,
      "max_score": null,
      "measured_at": "2026-09-10T09:49:09Z",
      "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": 219,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.7511685714164,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 11.967580414073916,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 46,
      "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": 23,
      "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": "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": 1,
      "max_score": null,
      "measured_at": "2026-07-31T03:32:11Z",
      "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": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.0720361138456,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 11.957291644537442,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 183,
      "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": 68,
      "draws": 157,
      "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": 18,
      "max_score": null,
      "measured_at": "2026-09-10T06:13:05Z",
      "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": 183,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.1968175126713,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 11.95411986023037,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "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": 66,
      "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": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-09-10T06:14:22Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.1881617549652,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 11.73718454940338,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 94,
      "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": 46,
      "draws": 84,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-04T08:44:46Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.947102088648,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 11.68296478061394,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 28.430533588759353,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "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": 32,
      "draws": 52,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-08-05T04:33:30Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.8127849964237,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 11.682283349084813,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 130,
      "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": 65,
      "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": "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": "2026-09-10T10:09:03Z",
      "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": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.5392311464016,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 11.392747323534184,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 268,
      "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": 99,
      "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": "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": 40,
      "max_score": null,
      "measured_at": "2026-09-10T09:53:50Z",
      "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": 268,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.8383584594383,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 11.367330732070096,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 92,
      "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": 46,
      "draws": 81,
      "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": 10,
      "max_score": null,
      "measured_at": "2026-07-31T03:32:23Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.5641394564377,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 11.325590947035412,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 166,
      "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": 63,
      "draws": 149,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-09-10T09:44:57Z",
      "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": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.6038125675204,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 11.223439055353664,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 136,
      "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": 64,
      "draws": 120,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:37Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.6475719484033,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 11.191453740660169,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 46,
      "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": 23,
      "draws": 45,
      "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": 1,
      "max_score": null,
      "measured_at": "2026-07-31T02:24:42Z",
      "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": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.4229747689012,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.940010823479835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "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": 29,
      "draws": 54,
      "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": 3,
      "max_score": null,
      "measured_at": "2026-08-03T05:47:14Z",
      "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": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.8573511124794,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.886852859373011,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 61,
      "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": "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": 12,
      "max_score": null,
      "measured_at": "2026-09-10T09:46:00Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.6936587759922,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.858956125600434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 352,
      "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": 176,
      "draws": 297,
      "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": 43,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:40Z",
      "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": 352,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.5194835765851,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.84501570624497,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.909379571113583,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "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": 54,
      "draws": 99,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:15Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.9640933137862,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.683228762592293,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "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": 31,
      "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": "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": 3,
      "max_score": null,
      "measured_at": "2026-08-03T04:41:42Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.451330904213,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.53671511272001,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "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": 53,
      "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": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-09-10T10:03:45Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.9811763064577,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.442043596500689,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 120,
      "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": 60,
      "draws": 104,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-09-10T06:14:09Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.1968307019079,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.355871463342384,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 56,
      "draws": 114,
      "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": 4,
      "max_score": null,
      "measured_at": "2026-09-10T07:12:57Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.4186117447339,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.341010847452775,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "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": 53,
      "draws": 99,
      "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": 7,
      "max_score": null,
      "measured_at": "2026-09-10T04:39:29Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.9891675947683,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.263403044539475,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 166,
      "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": 63,
      "draws": 147,
      "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": 10,
      "max_score": null,
      "measured_at": "2026-09-10T07:13:04Z",
      "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": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.1288826180637,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.237515749847217,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 174,
      "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": 66,
      "draws": 163,
      "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": 10,
      "max_score": null,
      "measured_at": "2026-09-10T07:14:16Z",
      "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": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.1410268131199,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.188518904480844,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 249,
      "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": 87,
      "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": "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": 37,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:45Z",
      "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": 249,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.2968136986608,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.025497046336621,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 104,
      "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": 52,
      "draws": 96,
      "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": 6,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:39Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.6921355670459,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 9.963827021369582,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "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": 53,
      "draws": 101,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-09-10T09:50:56Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.2790794804664,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 9.955451026536553,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "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": 80,
      "draws": 210,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-09-10T07:13:02Z",
      "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": 1434.5467518430132,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 9.845278217768804,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 104,
      "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": 52,
      "draws": 102,
      "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": 2,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:35Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.814937022176,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 9.805861440635663,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 102,
      "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": 2,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:58Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.5690635873218,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 9.761584645888398,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 454,
      "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": 156,
      "draws": 419,
      "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": 32,
      "max_score": null,
      "measured_at": "2026-09-10T09:49:08Z",
      "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": 1433.2751055672807,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 9.623986038775216,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 88,
      "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": 43,
      "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": "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": 3,
      "max_score": null,
      "measured_at": "2026-08-05T04:33:16Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.2026041849722,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 9.449979970240136,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "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": 55,
      "draws": 102,
      "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": 4,
      "max_score": null,
      "measured_at": "2026-09-10T07:14:22Z",
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.0385599177885,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 9.318441010342715,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "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": 66,
      "draws": 129,
      "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": 3,
      "max_score": null,
      "measured_at": "2026-09-10T09:45:47Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.4484210166358,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 9.262937256635835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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:thinkingmachines-inkling:281eafa14f6ff011",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 72,
      "draws": 200,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:58Z",
      "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": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.8631926503854,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 9.050334687326071,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 82,
      "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": 41,
      "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": "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": 5,
      "max_score": null,
      "measured_at": "2026-08-05T04:26:48Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.1572953479408,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 8.990579277651428,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "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": 53,
      "draws": 101,
      "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": 4,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:35Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.700789284466,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 8.950914647096557,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 112,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-09-10T07:13:19Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.1967788196498,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 8.860426297576485,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 462,
      "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": 161,
      "draws": 418,
      "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": 40,
      "max_score": null,
      "measured_at": "2026-09-10T09:49:09Z",
      "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": 462,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.613616977331,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 8.821204616548417,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 106,
      "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": 53,
      "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": "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": 3,
      "max_score": null,
      "measured_at": "2026-09-10T09:45:40Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.5809790659166,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 8.569180028204126,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 96,
      "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": 6,
      "max_score": null,
      "measured_at": "2026-09-10T09:45:47Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.390578828434,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 8.46888583743832,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "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": 55,
      "draws": 113,
      "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": 3,
      "max_score": null,
      "measured_at": "2026-09-10T09:44:42Z",
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.1998400127345,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 8.444620292408556,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 144,
      "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": 72,
      "draws": 130,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:59Z",
      "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": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.8897885177287,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 8.345895178371906,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 168,
      "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": 64,
      "draws": 147,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:56Z",
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.894017870154,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 8.247425935777672,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 104,
      "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": 52,
      "draws": 102,
      "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": 2,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:59Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.0754357256574,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 8.232055367080951,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "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-flash:22cd36959459fbdd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 93,
      "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": 4,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:46Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.2773847293352,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 8.088342646823264,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 96,
      "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": 6,
      "max_score": null,
      "measured_at": "2026-09-10T07:13:17Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.2629477789696,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 8.085742846285687,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "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": 55,
      "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": "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": 26,
      "max_score": null,
      "measured_at": "2026-09-10T07:14:27Z",
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.930131541753,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 8.038357928704011,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 93,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:52Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.2471822852578,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 7.902824182042486,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "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": 22,
      "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": "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": 6,
      "max_score": null,
      "measured_at": "2026-08-04T05:07:08Z",
      "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": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.1751466918467,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 7.834028495391087,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 2,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 98,
      "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": 6,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:45Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.1135913809594,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 7.518607942495322,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 166,
      "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": 63,
      "draws": 155,
      "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": 10,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:45Z",
      "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": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.8422506070183,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 7.484704864315055,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 52,
      "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": 26,
      "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": "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": 5,
      "max_score": null,
      "measured_at": "2026-07-31T02:27:36Z",
      "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": 52,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.3962138369807,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 7.405950095136704,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.930281974344517,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "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": 55,
      "draws": 102,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-09-10T06:12:24Z",
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.3963585232377,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 7.401997425923536,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "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": 38,
      "draws": 90,
      "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": 7,
      "max_score": null,
      "measured_at": "2026-08-05T04:27:03Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.4826319119566,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 7.0150208382150785,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 94,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:33Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.0357341877234,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 6.964348588339904,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 104,
      "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": 52,
      "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": "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": 4,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:47Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.4870377723773,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 6.865539546300709,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 90,
      "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": 6,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:43Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.2710673446647,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 6.646568053595592,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 200,
      "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": 68,
      "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": "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": 27,
      "max_score": null,
      "measured_at": "2026-09-10T09:49:03Z",
      "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": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.5529196297932,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 6.485222218768579,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 74,
      "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": 37,
      "draws": 68,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-08-03T14:15:10Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.3417075004436,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 6.451833831046862,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "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": 28,
      "draws": 54,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-03T08:16:45Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.5933872534667,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 6.27975662875229,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 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": 191,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-09-10T09:44:50Z",
      "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": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.4013902664049,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 6.242872745526706,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 117,
      "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": 56,
      "draws": 103,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:44Z",
      "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": 117,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.8623852821136,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 6.07109411954341,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.2787308949161655,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 90,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-09-10T09:49:00Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.9212187647054,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 5.142930493219368,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "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": 88,
      "draws": 203,
      "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": 31,
      "max_score": null,
      "measured_at": "2026-09-10T06:12:57Z",
      "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": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.6097196384471,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 4.775250900350241,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 168,
      "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": 64,
      "draws": 130,
      "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": 33,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:43Z",
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.789468639564,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 3.906687867060584,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 104,
      "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": 52,
      "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": "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": 9,
      "max_score": null,
      "measured_at": "2026-09-10T09:49:05Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.6961605830274,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 2.2211281793648086,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "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": 66,
      "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-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": "2026-09-10T11:06:16Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 2094.223525062207,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 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": 12,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:04Z",
      "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": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1992.7001425373535,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 89.4371849014492,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 232
    },
    {
      "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": 12,
      "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": 14,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:16Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1950.600091461118,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 85.0569619016003,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 106
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03: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": 66,
      "draws": 16,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-09-10T11:05:19Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1892.739852440075,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 79.03699890255805,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 212,
      "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": 86,
      "draws": 5,
      "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": 36,
      "max_score": null,
      "measured_at": "2026-09-10T11:01:05Z",
      "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": 211,
      "rating_method": "sequential_elo",
      "raw_elo": 1862.9174588920664,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 76.6845715154764,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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:GB2-03: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": 34,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:19Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1867.1321084211895,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 76.3726878991664,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 86
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "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": 66,
      "draws": 46,
      "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": 6,
      "max_score": null,
      "measured_at": "2026-09-10T10:59:10Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1849.1528943906224,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 74.50207337964267,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 138,
      "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": 66,
      "draws": 35,
      "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": 14,
      "max_score": null,
      "measured_at": "2026-09-10T11:00:17Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1816.03943786734,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 71.05684421340891,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 114,
      "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": 57,
      "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",
        "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": 12,
      "max_score": null,
      "measured_at": "2026-08-05T04:20:59Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1802.657390906043,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 67.80798395215069,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.910536671832062,
      "unilateral_faults": 0,
      "wins": 98
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 72,
      "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": 34,
      "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": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:17:00Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1793.0866148930616,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 65.43559754230012,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 38.449493652678655,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "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": 66,
      "draws": 47,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-09-10T11:00:18Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1699.1383870159802,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 58.89408767141809,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 138,
      "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": 66,
      "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": "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": 43,
      "max_score": null,
      "measured_at": "2026-09-10T10:58:44Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1691.0287691045999,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 58.05033727237247,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "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": 66,
      "draws": 57,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-09-10T10:58:46Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1677.1243031299484,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 56.603672479674294,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "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": 66,
      "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": "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": 39,
      "max_score": null,
      "measured_at": "2026-09-10T10:57:29Z",
      "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": 131,
      "rating_method": "sequential_elo",
      "raw_elo": 1677.0077846493843,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 56.577906094603094,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:qwen-qwen3-8-flash:98dfb2fac355b676",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 32,
      "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": 40,
      "max_score": null,
      "measured_at": "2026-09-10T10:58:11Z",
      "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": 131,
      "rating_method": "sequential_elo",
      "raw_elo": 1674.4366977746672,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 56.31040205184428,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03: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": 66,
      "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": "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": 40,
      "max_score": null,
      "measured_at": "2026-09-10T11:00:26Z",
      "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": 131,
      "rating_method": "sequential_elo",
      "raw_elo": 1664.6913668946706,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.29646688144744,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 138,
      "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": 66,
      "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": "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": 39,
      "max_score": null,
      "measured_at": "2026-09-10T11:00:55Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1657.7631805155133,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.5892798029273,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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:GB2-03: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": 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-5.6-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": 75,
      "max_score": null,
      "measured_at": "2026-09-10T11:01:12Z",
      "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": 209,
      "rating_method": "sequential_elo",
      "raw_elo": 1649.65448556946,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.48243593724166,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 5,
      "attempted_matches": 769,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:stealth-ox-alpha:fe3b437dca2c4367",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 5,
      "distinct_rated_opponents": 330,
      "draws": 148,
      "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": 173,
      "max_score": null,
      "measured_at": "2026-09-10T11:01:05Z",
      "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": 632,
      "rating_method": "sequential_elo",
      "raw_elo": 1656.300862782808,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.34658467999775,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.009000729485333,
      "unilateral_faults": 131,
      "wins": 311
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "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": 66,
      "draws": 39,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-09-10T11:00:45Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1617.6146281467568,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.41209692545726,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "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": 66,
      "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": "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": 35,
      "max_score": null,
      "measured_at": "2026-09-10T11:00:08Z",
      "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": 131,
      "rating_method": "sequential_elo",
      "raw_elo": 1616.442752927784,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.27652787410777,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "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": 66,
      "draws": 22,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-09-10T10:57:55Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1598.6883574866376,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.442947626880404,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-5-flash:79befaaad7974375",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 35,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-09-10T11:00:21Z",
      "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": 131,
      "rating_method": "sequential_elo",
      "raw_elo": 1586.9153526524012,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.204403387185614,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "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": 66,
      "draws": 46,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-09-10T11:01:01Z",
      "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": 131,
      "rating_method": "sequential_elo",
      "raw_elo": 1571.8773387262142,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.63980066610449,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 130,
      "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": 65,
      "draws": 25,
      "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": 39,
      "max_score": null,
      "measured_at": "2026-08-05T05:24:31Z",
      "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": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1580.2505939427776,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.00659226242805,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.8435026888779,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:thinkingmachines-inkling:b27963da4b6944f2",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 90,
      "draws": 51,
      "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": 80,
      "max_score": null,
      "measured_at": "2026-09-10T04:29:56Z",
      "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": 247,
      "rating_method": "sequential_elo",
      "raw_elo": 1543.8740996061813,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.70587386646689,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:tencent-hy4-preview:b8e7119f660161ad",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 55,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-09-10T10:51:41Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1551.2923629511429,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.511717852618325,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-6-flash:b4583ef7c04d45cd",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 89,
      "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-3.6-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": 73,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:39Z",
      "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": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1542.5270863810842,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.44619039396651,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 58,
      "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": 29,
      "draws": 18,
      "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": 19,
      "max_score": null,
      "measured_at": "2026-08-05T04:02:51Z",
      "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": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.346999402338,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.06053158843793,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "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": 66,
      "draws": 69,
      "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": 36,
      "max_score": null,
      "measured_at": "2026-09-10T10:51:20Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.1575815875583,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.87343571896586,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:moonshotai-kimi-k3:6a00f2f5a49a8584",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 90,
      "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": "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": 64,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:09Z",
      "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": 241,
      "rating_method": "sequential_elo",
      "raw_elo": 1532.8658749771148,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.5279830685233,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 7,
      "attempted_matches": 1051,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:stealth-ox-alpha:6719f8157bcde29f",
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 7,
      "distinct_rated_opponents": 522,
      "draws": 206,
      "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": 412,
      "max_score": null,
      "measured_at": "2026-09-10T11:01:27Z",
      "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": 1042,
      "rating_method": "sequential_elo",
      "raw_elo": 1538.0029662977238,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.32178294840338,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 424
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 152,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:z-ai-glm-5-3-flash:22cd36959459fbdd",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 76,
      "draws": 49,
      "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": 63,
      "max_score": null,
      "measured_at": "2026-09-10T03:39:37Z",
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.4143934644067,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.207884772462265,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 270,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:moonshotai-kimi-k3:f0bfe8c58b2cc988",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "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": "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": 105,
      "max_score": null,
      "measured_at": "2026-09-10T07:38:27Z",
      "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": 270,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.2359495190115,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.089418073261065,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 140,
      "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": 67,
      "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": "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": 54,
      "max_score": null,
      "measured_at": "2026-09-10T07:36:12Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.6857905884385,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.018834351295574,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 234,
      "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": 95,
      "draws": 90,
      "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": 84,
      "max_score": null,
      "measured_at": "2026-09-10T07:45:26Z",
      "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": 233,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.9590436872616,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.97211414971662,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 144,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:qwen-qwen3-8-max:644816d2bc8a5f5c",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 71,
      "draws": 48,
      "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": 56,
      "max_score": null,
      "measured_at": "2026-09-10T10:47:44Z",
      "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": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.1049810468219,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.5639073510403,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 292,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-4-5:e2ff6744eb1bb7c6",
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 130,
      "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": 95,
      "max_score": null,
      "measured_at": "2026-09-10T07:01:33Z",
      "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": 291,
      "rating_method": "sequential_elo",
      "raw_elo": 1521.0234426696943,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.5356517346492,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 162,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:bytedance-seed-seed-2-0-code:2447db730c8d12fe",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 41,
      "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": 84,
      "max_score": null,
      "measured_at": "2026-09-10T08:14:45Z",
      "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": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1525.3993880554747,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.16668933391658,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-5-flash:188028ef432c73f8",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 45,
      "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": 46,
      "max_score": null,
      "measured_at": "2026-09-10T10:48:35Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.9956475562567,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.08785360578334,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 154,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:qwen-qwen3-8-flash:e1a2822fb5bba20e",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 53,
      "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": 65,
      "max_score": null,
      "measured_at": "2026-09-10T10:49:31Z",
      "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": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.3440787059294,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 40.141482789051,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:meta-muse-spark-1-2:0ef600658249027b",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 99,
      "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": "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": 97,
      "max_score": null,
      "measured_at": "2026-09-10T10:59:40Z",
      "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": 249,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.8099657675816,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.96423888645114,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 564,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-6-flash:b574aaabaed70f28",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 210,
      "draws": 169,
      "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": 192,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:09Z",
      "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": 563,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.0737878225204,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.31324742201342,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 151,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:qwen-qwen3-8-max:7b21229bd01e0b5e",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 74,
      "draws": 22,
      "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": 74,
      "max_score": null,
      "measured_at": "2026-09-10T05:10:55Z",
      "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": 151,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.677115528226,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.20691764507233,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-4-5:959db58a0f4d59b9",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 43,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-08-05T02:50:27Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.9730430010436,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 38.77747256709314,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 210,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-sonnet-5:a86621e2793b5dec",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 86,
      "draws": 73,
      "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": 79,
      "max_score": null,
      "measured_at": "2026-09-10T10:49:31Z",
      "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": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.3697647442227,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 38.22889075944164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 55,
      "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": 26,
      "draws": 16,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-08-03T14:17:00Z",
      "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": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1515.9921221734,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.83597213035345,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 254,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:meta-muse-spark-1-2:539f99e7c4c4b6ea",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 97,
      "draws": 41,
      "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": 110,
      "max_score": null,
      "measured_at": "2026-09-10T08:23:31Z",
      "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": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.219015697014,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.43165107800999,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03: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": 35,
      "draws": 25,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-05T04:02:45Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.2178560792047,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.07546402146493,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 284,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-5-flash-lite:55634764b9427e4e",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 99,
      "draws": 78,
      "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": 96,
      "max_score": null,
      "measured_at": "2026-09-10T11:01:22Z",
      "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": 284,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.427549109553,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 36.970068726699864,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 70,
      "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": 35,
      "draws": 26,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-08-05T03:55:23Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.939205942563,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 36.838386025548644,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 186,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:78fb6a9e00356b09",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 92,
      "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/qwen3.8-2.4t-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": 67,
      "max_score": null,
      "measured_at": "2026-09-10T10:48:35Z",
      "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": 183,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.1251507851525,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 36.7519074126838,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-8-flash:83795e08736dcbd6",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "draws": 40,
      "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": 64,
      "max_score": null,
      "measured_at": "2026-09-10T08:26:53Z",
      "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": 149,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.9781721136667,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 36.71877479296601,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 56,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:x-ai-grok-4-5:a7aa1873ad17dbcc",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "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": "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": 20,
      "max_score": null,
      "measured_at": "2026-08-05T05:42:30Z",
      "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": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.227845346718,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 36.50322253143216,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:thinkingmachines-inkling:a1a9848a1d14b67e",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 60,
      "draws": 55,
      "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": 31,
      "max_score": null,
      "measured_at": "2026-08-05T05:16:45Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.7385328418418,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 36.30519910226115,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:deepseek-deepseek-v4-pro:42034002bcfc5f74",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 49,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-09-10T08:26:55Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.430332315426,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 36.03496399223896,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-sol:e7389fafab42de55",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 91,
      "draws": 87,
      "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": 84,
      "max_score": null,
      "measured_at": "2026-09-10T09:46:08Z",
      "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": 241,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.111465965465,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.47859920538773,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 198,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:x-ai-grok-4-6:d94ddefd8b9f53eb",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 99,
      "draws": 50,
      "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": 73,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:19Z",
      "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": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.3750031545576,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.43919418965659,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 61,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-4-mini:e296afd987da0af3",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 33,
      "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": 14,
      "max_score": null,
      "measured_at": "2026-08-05T06:55:18Z",
      "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": 61,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.3280415856061,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.38802948398163,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.750063500095248,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:deepseek-deepseek-v4-flash:dac448fbfe2a5737",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 16,
      "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": "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": 12,
      "max_score": null,
      "measured_at": "2026-07-31T02:50:29Z",
      "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": 32,
      "rating_method": "sequential_elo",
      "raw_elo": 1506.8053924803423,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.24719032759922,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 43.288827977848925,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:f9ec308f9bb8850b",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "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": "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": 61,
      "max_score": null,
      "measured_at": "2026-09-10T08:25:04Z",
      "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": 131,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.4206644122155,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.18796927707111,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 146,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:qwen-qwen3-8-27b:47ad2584aeb815bb",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "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": "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": 69,
      "max_score": null,
      "measured_at": "2026-09-10T07:03:39Z",
      "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": 145,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.9893251701199,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.009010479559414,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 142,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:bytedance-seed-seed-2-0-code:e037862ab5c7ecb3",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 68,
      "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": "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": 64,
      "max_score": null,
      "measured_at": "2026-09-10T06:07:18Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.26607299235,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.82242746606155,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 14,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-07-31T01:23:54Z",
      "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": 36,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.6641920483735,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.802953750960214,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 38.449493652678655,
      "unilateral_faults": null,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 164,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:meta-muse-spark-1-3:22ddc49b675eb171",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "draws": 38,
      "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": 55,
      "max_score": null,
      "measured_at": "2026-09-10T06:52:41Z",
      "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": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.393382702446,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.5705964315616,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 210,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:meta-muse-spark-1-2:c4024993f2e98d89",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "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": "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": 89,
      "max_score": null,
      "measured_at": "2026-09-10T10:54:31Z",
      "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": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.8229907189177,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.42644833802889,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 60,
      "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": 30,
      "draws": 55,
      "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": 4,
      "max_score": null,
      "measured_at": "2026-08-05T04:03:00Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.7645713367565,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.349868844232375,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 302,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:thinkingmachines-inkling:281eafa14f6ff011",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 122,
      "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": 107,
      "max_score": null,
      "measured_at": "2026-09-10T08:21:00Z",
      "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": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.964326697737,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.083009309825044,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:xiaomi-mimo-v2-5:35035a0b78826dbc",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "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": "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": 19,
      "max_score": null,
      "measured_at": "2026-08-05T04:02:34Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.5650571562767,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.912938053620756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 212,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-sonnet-5:73f1b29a5c45562d",
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "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-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": 69,
      "max_score": null,
      "measured_at": "2026-09-10T08:12:13Z",
      "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": 212,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.3066313675868,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.86599146220886,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:nex-agi-nex-n2-pro:b04b6e7c11ec4633",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 19,
      "draws": 26,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-03T15:07:00Z",
      "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": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.8177473760302,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.75354537169144,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 32.49928516630233,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 268,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:moonshotai-kimi-k3:ccf8a3c1c9260d55",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 97,
      "draws": 124,
      "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": 86,
      "max_score": null,
      "measured_at": "2026-09-10T08:15:07Z",
      "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": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.238678577864,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.72808628713718,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 172,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:thinkingmachines-inkling-small:c4a079d6b58a2c73",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "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": "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": 51,
      "max_score": null,
      "measured_at": "2026-09-10T10:55:16Z",
      "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": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.6089243701294,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.68895206775385,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 196,
      "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": 95,
      "draws": 30,
      "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": 99,
      "max_score": null,
      "measured_at": "2026-09-10T10:54:56Z",
      "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": 190,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.207793643488,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.071697400705354,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-luna:e05ef4cc93414f96",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 92,
      "draws": 115,
      "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": 70,
      "max_score": null,
      "measured_at": "2026-09-10T10:52:53Z",
      "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": 237,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.133702959996,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.06553227928354,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:z-ai-glm-5-2:5ea14bc9644b6a2b",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 38,
      "draws": 37,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-07-31T01:34:27Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.3016164611427,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.06360879194405,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 36.393187298490844,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-4-8:8ccf8977401d94db",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "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-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": 10,
      "max_score": null,
      "measured_at": "2026-08-03T10:31:14Z",
      "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": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.0280879589282,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.01106956211032,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 144,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:inception-mercury-2-5-preview:df3dbf369397b893",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 72,
      "draws": 50,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-09-10T08:26:27Z",
      "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": 143,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.9077002269778,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.687732040284814,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 494,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-6-flash:13a24e3021af753a",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 186,
      "draws": 125,
      "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": 215,
      "max_score": null,
      "measured_at": "2026-09-10T10:59:04Z",
      "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": 492,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.8610019118303,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.56614014388901,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 52,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:36d8ebdcb946256c",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 24,
      "draws": 28,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-08-05T03:54:51Z",
      "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": 52,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.1418660952263,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.12832035449617,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.930281974344517,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 268,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:meituan-longcat-2-0:bed5035a5082adf8",
      "capped_draws": 38,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 91,
      "draws": 123,
      "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": 81,
      "max_score": null,
      "measured_at": "2026-09-10T08:26:41Z",
      "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": 267,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.2272237880622,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.878168765270942,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 43,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5:16f7def69ce10ccd",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 17,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-08-03T03:06:54Z",
      "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": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.0397619411053,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.59173778794821,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 32.49928516630233,
      "unilateral_faults": 1,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:bytedance-seed-seed-2-0-code:c69120230888411c",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 57,
      "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": 34,
      "max_score": null,
      "measured_at": "2026-09-10T10:47:25Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.4878724405924,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.56709410597149,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 257,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-luna:29e28a5adce9180a",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 94,
      "draws": 103,
      "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": 84,
      "max_score": null,
      "measured_at": "2026-09-10T11:01:12Z",
      "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": 257,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.6322402370815,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.559379754277902,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:o3:1084c60ee563e860",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 83,
      "draws": 89,
      "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": 90,
      "max_score": null,
      "measured_at": "2026-09-10T10:50:33Z",
      "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": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.5139023514475,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.45724153790146,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 68,
      "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": 33,
      "draws": 22,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-05T02:49:50Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.4673153903937,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.307974629209557,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:x-ai-grok-4-5:5e133fd8ec34ed0c",
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 86,
      "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": "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": 74,
      "max_score": null,
      "measured_at": "2026-09-10T10:53:15Z",
      "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": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.539339692124,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.138548110434098,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 46,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:qwen-qwen3-7-max:a92ef5f3c3f212e3",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 21,
      "draws": 37,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-08-03T04:31:38Z",
      "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": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.388701186896,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.86368222336517,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:deepseek-deepseek-v4-flash:14b865d3f352c468",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 68,
      "draws": 84,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-09-10T06:53:31Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.4945219790866,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.78851218219209,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 138,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:deepseek-deepseek-v4-flash:e0a2978fff9e81b1",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "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": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-09-10T03:39:11Z",
      "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": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.8880325254963,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.23086777854394,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-5:1a25631bf54a6363",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "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-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": 18,
      "max_score": null,
      "measured_at": "2026-08-03T11:59:49Z",
      "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": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.4311911915072,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.16793741587809,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 11
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1182,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:stealth-ox-alpha:dfb3dd7361cfa1a2",
      "capped_draws": 70,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 8,
      "distinct_rated_opponents": 589,
      "draws": 619,
      "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": 300,
      "max_score": null,
      "measured_at": "2026-09-10T11:01:03Z",
      "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": 1176,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.9381118969159,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.80876763063011,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 257
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 298,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-4:672219b99ff5a80c",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "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": "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": 83,
      "max_score": null,
      "measured_at": "2026-09-10T08:14:09Z",
      "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": 292,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.118451422626,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.79281756153531,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 140,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:deepseek-deepseek-v4-pro:c11fecb63644464d",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 70,
      "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-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": 37,
      "max_score": null,
      "measured_at": "2026-09-10T05:13:50Z",
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.4734243744404,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.588595959202145,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 353,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:poolside-laguna-s-2-1:533b6103a5973424",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 142,
      "draws": 149,
      "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": 109,
      "max_score": null,
      "measured_at": "2026-09-10T08:23:32Z",
      "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": 353,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.6522280882073,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.541446134255093,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.385286799032644,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 510,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-5-flash-lite:5943a501fa6113ab",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 182,
      "draws": 120,
      "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": 181,
      "max_score": null,
      "measured_at": "2026-09-10T10:57:37Z",
      "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": 510,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.4432366699407,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.338111214731462,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 209
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-5:53d4c02c8a9496db",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "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-5.5",
        "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": 22,
      "max_score": null,
      "measured_at": "2026-08-05T05:23:57Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.1227478123901,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.247491079096818,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:z-ai-glm-5-3:9e30a36ab00bd740",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 64,
      "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": 34,
      "max_score": null,
      "measured_at": "2026-09-10T10:46:15Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.0235523274969,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.22983490746917,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:45ec16f47504b5f5",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "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-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": 42,
      "max_score": null,
      "measured_at": "2026-09-10T10:53:34Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.4341881071348,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.960429231630975,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:meta-muse-glimmer-30b:a614a905445f79d1",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 65,
      "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": 35,
      "max_score": null,
      "measured_at": "2026-09-10T10:54:45Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.0678585135524,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.71422878659438,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 499,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-5-flash-lite:0bab1c3ea19c7cb7",
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 178,
      "draws": 233,
      "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": 162,
      "max_score": null,
      "measured_at": "2026-09-10T10:48:47Z",
      "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": 499,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.7777990120844,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.622810270087797,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:tencent-hy4-preview:014a9ceb67d5b786",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 93,
      "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": 25,
      "max_score": null,
      "measured_at": "2026-09-10T10:52:41Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.3610086540643,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.53664270722644,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 162,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-terra:bd3aacb7be18fc49",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 71,
      "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": 54,
      "max_score": null,
      "measured_at": "2026-09-10T05:53:10Z",
      "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": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.4320852241547,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.37278067295601,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:z-ai-glm-5-2:184634950256ca6a",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 59,
      "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": 42,
      "max_score": null,
      "measured_at": "2026-09-10T10:53:32Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.4307015093464,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.335807422329626,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:nex-agi-nex-n2-pro:a8c61d4550659ad0",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 22,
      "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": "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": 16,
      "max_score": null,
      "measured_at": "2026-08-04T08:55:37Z",
      "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": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.750666950453,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.11331182821081,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.678571428571434,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03: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": 23,
      "draws": 19,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-08-03T12:01:44Z",
      "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": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.2542829519666,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.075364138283934,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.264004201400486,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 536,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:poolside-laguna-s-2-1:07eac22bdea1b9b3",
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 186,
      "draws": 223,
      "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": 201,
      "max_score": null,
      "measured_at": "2026-09-10T10:57:42Z",
      "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": 536,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.963147228935,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.00561511750182,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 36,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:z-ai-glm-5-2:f14efcbac580ffaa",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 18,
      "draws": 26,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-07-31T02:57:05Z",
      "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": 36,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.0275376622074,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.86986462841452,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 38.449493652678655,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 144,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:thinkingmachines-inkling-small:f1451a0a6af20650",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 70,
      "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": "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": 21,
      "max_score": null,
      "measured_at": "2026-09-10T10:44:28Z",
      "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": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.6149135142155,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.77922001165981,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:openai-gpt-oss-120b:07d17099885c6bdb",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 49,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-09-10T10:51:43Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1397.508419898018,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.51154808681522,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "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": 66,
      "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": "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": 42,
      "max_score": null,
      "measured_at": "2026-09-10T10:55:16Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.9860745205874,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.04102891334411,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 245,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-4:483e8409583d40a0",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 87,
      "draws": 84,
      "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": 79,
      "max_score": null,
      "measured_at": "2026-09-10T05:21:04Z",
      "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": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1382.2840850584937,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.86648580703239,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 34,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:be72f75fe8d3007b",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 17,
      "draws": 24,
      "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": 7,
      "max_score": null,
      "measured_at": "2026-07-31T02:59:43Z",
      "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": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.039014779849,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.845947820192375,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 40.76542547285167,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "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": 66,
      "draws": 120,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-09-10T10:48:58Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1390.7525411421307,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.808645008214626,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 46,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5:3bb27dbc092c7ff2",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 22,
      "draws": 24,
      "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": 14,
      "max_score": null,
      "measured_at": "2026-08-05T01:53:39Z",
      "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": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.8505029015237,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.750002522868716,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:z-ai-glm-5-2:20c65e2b7513d4b4",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 78,
      "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": 28,
      "max_score": null,
      "measured_at": "2026-09-10T10:50:10Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1389.496297577414,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.677941438624654,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-4-5:9f0371e603fb81bd",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 94,
      "draws": 74,
      "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": 84,
      "max_score": null,
      "measured_at": "2026-09-10T08:16:08Z",
      "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": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1377.7612868151043,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.438809841777037,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 145,
      "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": 68,
      "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": "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": 41,
      "max_score": null,
      "measured_at": "2026-09-10T10:54:12Z",
      "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": 145,
      "rating_method": "sequential_elo",
      "raw_elo": 1384.5499476251923,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.327712683660216,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:deepseek-deepseek-v4-pro:c37d073d6b142a09",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "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": "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": 59,
      "max_score": null,
      "measured_at": "2026-09-10T10:50:08Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1385.0409301782825,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.214390866699837,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:meta-muse-glimmer-30b:085624a1bd2a3883",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 66,
      "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": 39,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:21Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1381.5176225686357,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.84781475496612,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 134,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:openai-gpt-oss-120b:7e4ecfa424847773",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 63,
      "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": 34,
      "max_score": null,
      "measured_at": "2026-09-10T10:49:44Z",
      "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": 133,
      "rating_method": "sequential_elo",
      "raw_elo": 1380.206473148802,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.724889026864293,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 130,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:meituan-longcat-2-0:45102822fc5f9296",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 61,
      "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": "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": 40,
      "max_score": null,
      "measured_at": "2026-08-05T05:24:42Z",
      "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": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1394.540988611574,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.677678742623275,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.928761438070325,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-fable-5:346aadd5d76b812b",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 76,
      "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": 35,
      "max_score": null,
      "measured_at": "2026-09-10T10:53:25Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1377.4522396482325,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.424839406577654,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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-5-6-terra:4506b3e0a8fb5629",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 79,
      "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": 37,
      "max_score": null,
      "measured_at": "2026-09-10T10:54:56Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1373.9942208454174,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.065056149626912,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:openai-gpt-oss-120b:59563b7e90e4a253",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 63,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-09-10T10:52:53Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1370.6296442485063,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.714994916497854,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "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": 66,
      "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": "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": 42,
      "max_score": null,
      "measured_at": "2026-09-10T10:54:11Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1365.9686904077316,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.230054478358582,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 214,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-4:cea8a68bd875deb9",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 115,
      "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": 68,
      "max_score": null,
      "measured_at": "2026-09-10T10:54:31Z",
      "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": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1356.2119695135434,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.985334973637,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 143,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:qwen-qwen3-8-max:a791831295f0ee80",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 68,
      "draws": 76,
      "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": 37,
      "max_score": null,
      "measured_at": "2026-09-10T10:49:44Z",
      "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": 143,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.2533801623117,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.67194141579853,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 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": 17,
      "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": 18,
      "max_score": null,
      "measured_at": "2026-08-05T04:21:17Z",
      "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": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.8618585327608,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.98682614510266,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 68.15840602663853,
      "unilateral_faults": null,
      "wins": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 156,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03: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": 60,
      "draws": 64,
      "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": 63,
      "max_score": null,
      "measured_at": "2026-08-05T05:24:14Z",
      "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": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1363.2902103171728,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.87323324614359,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.558578456903872,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03: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": 66,
      "draws": 78,
      "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": 42,
      "max_score": null,
      "measured_at": "2026-09-10T10:58:30Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1330.0461612539777,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.492560475629574,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "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": 66,
      "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": "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": 30,
      "max_score": null,
      "measured_at": "2026-09-10T11:00:35Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1328.441766750424,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.32563417683313,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 210,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-luna:15a0f0a09f9eb8e5",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "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-5.6-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": 74,
      "max_score": null,
      "measured_at": "2026-09-10T11:01:22Z",
      "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": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1301.546731566777,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 18.271013266534894,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:z-ai-glm-5-2:4571486d5f3c5826",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 78,
      "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": 50,
      "max_score": null,
      "measured_at": "2026-09-10T10:59:37Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1296.3099172955706,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 16.982534527025862,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-fable-5:1f4ca1763387a608",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 45,
      "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": 75,
      "max_score": null,
      "measured_at": "2026-09-10T10:58:55Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1235.3161010419403,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.636544202241724,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-5-flash:e1e7937be001cd2a",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 39,
      "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": 72,
      "max_score": null,
      "measured_at": "2026-09-10T11:00:53Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1219.7338249759325,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 9.01531471986587,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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:GB2-03: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": 96,
      "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": "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": 174,
      "max_score": null,
      "measured_at": "2026-09-10T11:01:12Z",
      "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": 268,
      "rating_method": "sequential_elo",
      "raw_elo": 1122.7881106713216,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 114,
      "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": 57,
      "draws": 10,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-09-10T10:08:45Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1907.4055627869584,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 98.28111373405677,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 99
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "draws": 14,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-09-10T10:10:05Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1883.1951086512008,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 94.27440970618706,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 92
    },
    {
      "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": 14,
      "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": 29,
      "max_score": null,
      "measured_at": "2026-09-10T10:10:08Z",
      "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": 1848.9541347501813,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 88.60770691415766,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 185
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "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": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-09-10T10:09:42Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1826.3218602875163,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 84.862183400186,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 86
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "draws": 16,
      "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": 21,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:02Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1818.160443932235,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 83.51151151272518,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 186,
      "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": 77,
      "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": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-09-10T10:06:17Z",
      "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": 186,
      "rating_method": "sequential_elo",
      "raw_elo": 1799.4467778247522,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 81.74661371399337,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 186,
      "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": 76,
      "draws": 43,
      "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": 21,
      "max_score": null,
      "measured_at": "2026-09-10T10:00:41Z",
      "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": 186,
      "rating_method": "sequential_elo",
      "raw_elo": 1740.1002470017625,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 71.92507204628161,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 114,
      "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": 57,
      "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-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": 23,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:46Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1746.4555040374125,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 71.64471752845151,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "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": 91,
      "draws": 75,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-09-10T09:54:08Z",
      "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": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1699.4440706751725,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 65.77337510145159,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 112,
      "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": 47,
      "draws": 19,
      "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": 14,
      "max_score": null,
      "measured_at": "2026-08-05T04:13:16Z",
      "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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1722.0204237619773,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 65.0016466552378,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.507220868368073,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 342,
      "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": 171,
      "draws": 112,
      "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": 64,
      "max_score": null,
      "measured_at": "2026-09-10T10:15:30Z",
      "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": 342,
      "rating_method": "sequential_elo",
      "raw_elo": 1682.6073396219508,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 61.078178953791536,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 166
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "draws": 16,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-09-10T09:56:41Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1670.008152813912,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 58.99307917629111,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "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": "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": 30,
      "max_score": null,
      "measured_at": "2026-09-10T09:56:35Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1651.3628695260552,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.90738193032783,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "draws": 20,
      "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": 40,
      "max_score": null,
      "measured_at": "2026-09-10T09:57:26Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1636.7722908196843,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.49271716840484,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 54
    },
    {
      "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": 44,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-09-10T09:57:01Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1632.0099106719301,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 52.70456806499455,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "draws": 40,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-09-10T09:56:27Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1625.6665151364496,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 51.654769151687816,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 127,
      "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": 61,
      "draws": 52,
      "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": 26,
      "max_score": null,
      "measured_at": "2026-09-10T09:57:17Z",
      "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": 127,
      "rating_method": "sequential_elo",
      "raw_elo": 1617.0984767902028,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.55866652707872,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.444173824159213,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "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": 28,
      "draws": 24,
      "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": 10,
      "max_score": null,
      "measured_at": "2026-08-05T01:54:41Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1622.394595844658,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.94611757043748,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 28
    },
    {
      "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": 35,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-09-10T09:52:53Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1582.7585448506213,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.553723611281114,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "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": 33,
      "draws": 46,
      "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": 3,
      "max_score": null,
      "measured_at": "2026-08-05T04:04:11Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1590.6223690206723,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.28025300648413,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "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": "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": 33,
      "max_score": null,
      "measured_at": "2026-09-10T09:53:09Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1580.7983584016195,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.22932296614858,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "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": "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": 59,
      "max_score": null,
      "measured_at": "2026-09-10T09:54:15Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1570.0749915745469,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.45466162285314,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 36
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 478,
      "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": 167,
      "draws": 131,
      "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": 147,
      "max_score": null,
      "measured_at": "2026-09-10T09:55:43Z",
      "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": 475,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.0651238854534,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.02102497124446,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 62,
      "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": 31,
      "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-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": 5,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:05Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1575.2825468133171,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.14931890005339,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 64,
      "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": 31,
      "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-v2.5-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": 12,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:01Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.6849655511323,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.69028173978519,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "draws": 38,
      "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": 40,
      "max_score": null,
      "measured_at": "2026-09-10T09:50:58Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.1136000673366,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.48214490364818,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 184,
      "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": 77,
      "draws": 90,
      "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": 42,
      "max_score": null,
      "measured_at": "2026-09-10T09:50:35Z",
      "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": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1541.4689786625354,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.02653543609264,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 189,
      "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": 79,
      "draws": 90,
      "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": 36,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:57Z",
      "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": 186,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.1929099684971,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 38.841449244307675,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 68,
      "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": 34,
      "draws": 37,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-05T03:47:20Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1558.1767288584622,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 38.689256035103924,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 15
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 362,
      "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": 181,
      "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": "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": 118,
      "max_score": null,
      "measured_at": "2026-09-10T09:52:47Z",
      "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": 362,
      "rating_method": "sequential_elo",
      "raw_elo": 1541.4198741744876,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.87091498905499,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.9168269413437915,
      "unilateral_faults": 0,
      "wins": 99
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 146,
      "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": 73,
      "draws": 66,
      "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": 34,
      "max_score": null,
      "measured_at": "2026-08-05T03:57:28Z",
      "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": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1548.6162307333443,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.38045751660635,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.377800258513929,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 138,
      "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": 69,
      "draws": 52,
      "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": 38,
      "max_score": null,
      "measured_at": "2026-08-05T03:54:42Z",
      "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": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.3733833554654,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 36.957881306791684,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.016004726288628,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "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": "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": 35,
      "max_score": null,
      "measured_at": "2026-09-10T09:50:27Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1533.4049458340203,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 36.38596009636121,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "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": 24,
      "draws": 27,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-07-31T02:32:56Z",
      "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": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.4826607753314,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.43189092678594,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.678571428571434,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "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": 34,
      "draws": 48,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-05T04:03:31Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1534.830093500697,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.04692207446579,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "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": 67,
      "draws": 63,
      "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": 40,
      "max_score": null,
      "measured_at": "2026-09-10T00:27:17Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.4638147130581,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.568416069453946,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 134,
      "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": 67,
      "draws": 70,
      "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": 38,
      "max_score": null,
      "measured_at": "2026-09-10T01:13:16Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.4972986814284,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.24296791137236,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 134,
      "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": 67,
      "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": "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": 50,
      "max_score": null,
      "measured_at": "2026-09-10T03:14:23Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.5664267801203,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.09594472015491,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 266,
      "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": 98,
      "draws": 129,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-09-10T07:13:18Z",
      "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": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.7041047211976,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.944449816020683,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 84,
      "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": 38,
      "draws": 52,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-05T05:03:39Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.912180056845,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.82886597508527,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 2,
      "attempted_matches": 464,
      "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": 170,
      "draws": 286,
      "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": 87,
      "max_score": null,
      "measured_at": "2026-09-10T09:50:35Z",
      "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": 458,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.1763575802674,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.70885960900305,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 140,
      "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": 70,
      "draws": 64,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-09-10T04:42:31Z",
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.9994974820688,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.628175763052685,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 104,
      "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": 52,
      "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",
        "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": 5,
      "max_score": null,
      "measured_at": "2026-07-31T02:31:22Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.8323226969433,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.37278856274247,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 25.077594640911812,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "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": 66,
      "draws": 61,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-09-10T07:13:46Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.39421628638,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.362787798826755,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 46,
      "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": 23,
      "draws": 30,
      "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": 6,
      "max_score": null,
      "measured_at": "2026-08-05T03:48:07Z",
      "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": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1517.7254552578606,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.308115130799013,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "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": 33,
      "draws": 59,
      "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": 3,
      "max_score": null,
      "measured_at": "2026-08-05T04:04:06Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1506.5088333178212,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.138488502474974,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 140,
      "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": 70,
      "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": "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": 44,
      "max_score": null,
      "measured_at": "2026-09-10T05:33:29Z",
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.2374098132043,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.674580273173802,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 76,
      "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": 36,
      "draws": 61,
      "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": 7,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:10Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.9648602725551,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.646329769358474,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 142,
      "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": 71,
      "draws": 83,
      "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": 42,
      "max_score": null,
      "measured_at": "2026-09-10T05:30:24Z",
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.3460835073072,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.566192792814146,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 120,
      "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": 60,
      "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": "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": 58,
      "max_score": null,
      "measured_at": "2026-09-10T04:01:53Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.9508346481748,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.515021005587823,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "draws": 58,
      "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": 33,
      "max_score": null,
      "measured_at": "2026-09-10T09:45:32Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.3894653501343,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.432616968483536,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 190,
      "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": 78,
      "draws": 122,
      "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": 42,
      "max_score": null,
      "measured_at": "2026-09-10T02:20:20Z",
      "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": 190,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.5368821382333,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.350634971233603,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 74,
      "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": 36,
      "draws": 49,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-08-05T01:02:26Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.6470368880275,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.32831260800084,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "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": 31,
      "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-3.1-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": 2,
      "max_score": null,
      "measured_at": "2026-08-04T03:46:58Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.4791598953682,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.022538939196433,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 2,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 133,
      "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": 62,
      "draws": 92,
      "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": 19,
      "max_score": null,
      "measured_at": "2026-09-10T06:15:45Z",
      "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": 133,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.0691796694814,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.17902200488099,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 222,
      "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": 90,
      "draws": 139,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-09-10T07:35:18Z",
      "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": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.1129279334805,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.982497616728754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 72,
      "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": 35,
      "draws": 58,
      "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": 7,
      "max_score": null,
      "measured_at": "2026-08-05T01:17:06Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.0137499861821,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.795545497153316,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 7
    },
    {
      "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": 69,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-08-05T01:16:32Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.3158309109629,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.751123392297373,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 35.48369970321018,
      "unilateral_faults": null,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "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": 38,
      "draws": 67,
      "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": 6,
      "max_score": null,
      "measured_at": "2026-08-05T02:13:44Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.8528084385841,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.572458734081646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "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": 66,
      "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": "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": 39,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:57Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.158184486332,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.34481954197784,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 143,
      "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": 69,
      "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": "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": 15,
      "max_score": null,
      "measured_at": "2026-09-10T10:08:59Z",
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.191931895889,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.223754441408413,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 64,
      "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": 27,
      "draws": 55,
      "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": 2,
      "max_score": null,
      "measured_at": "2026-08-04T02:50:00Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.0433924004185,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.208177713775562,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 2,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "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": 35,
      "draws": 65,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-08-05T03:57:28Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.6086038147535,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.170519861988716,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 4
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 366,
      "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": 183,
      "draws": 251,
      "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": 61,
      "max_score": null,
      "measured_at": "2026-09-10T09:51:11Z",
      "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": 365,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.7215980170065,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.868002662206536,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.4112147100384131,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "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": 36,
      "draws": 64,
      "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": 6,
      "max_score": null,
      "measured_at": "2026-08-03T11:50:25Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.185656143178,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.769534645413174,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "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": 40,
      "draws": 59,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-08-05T00:15:53Z",
      "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": 81,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.3132261970989,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.62770249214871,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 61,
      "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": "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": 46,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:18Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.5658380642715,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.52152714323692,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "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": 34,
      "draws": 55,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-05T03:48:11Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.423921097945,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.431101136188207,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "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": 32,
      "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-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": 11,
      "max_score": null,
      "measured_at": "2026-08-05T03:47:33Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.4910188022745,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.2110900930888,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 102,
      "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": 51,
      "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": "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": 22,
      "max_score": null,
      "measured_at": "2026-07-31T02:38:28Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.3484784117818,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.85911833115472,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.06502737020246,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "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": 43,
      "draws": 66,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-08-05T05:10:34Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.6741891937638,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.656853491070645,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 68,
      "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": 33,
      "draws": 46,
      "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": 10,
      "max_score": null,
      "measured_at": "2026-08-05T05:24:08Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.1917518609623,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.617653837866694,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 140,
      "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": 70,
      "draws": 78,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-09-10T07:13:06Z",
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.6448776444101,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.60464432138626,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 98,
      "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": 38,
      "draws": 86,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-08-05T05:33:25Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.8882535679693,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.22863025415459,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "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": 22,
      "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": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-30T18:04:01Z",
      "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": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.14911205402,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.201140195303772,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 30.785599249992988,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "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": 84,
      "draws": 145,
      "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": 51,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:38Z",
      "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": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.7324707966186,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.12586844413473,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 84,
      "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": 39,
      "draws": 69,
      "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": 10,
      "max_score": null,
      "measured_at": "2026-08-05T03:15:12Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.2736621572235,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.09637172241155,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "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": 30,
      "draws": 47,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-08-05T05:05:18Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.0998106127977,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.98788364443893,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "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": 32,
      "draws": 48,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-08-05T05:05:23Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.340762765141,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.862265180138433,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 184,
      "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": 92,
      "draws": 99,
      "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": 53,
      "max_score": null,
      "measured_at": "2026-09-10T10:15:30Z",
      "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": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.7570669799688,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.841660594454027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:xiaomi-mimo-v2-5:024b37c390436d5a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 42,
      "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": 7,
      "max_score": null,
      "measured_at": "2026-07-31T02:31:03Z",
      "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": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.8007459421844,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.5961118118581,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 198,
      "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": 81,
      "draws": 109,
      "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": 59,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:17Z",
      "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": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.1966197661275,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.592241653411964,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 222,
      "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": 83,
      "draws": 146,
      "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": 39,
      "max_score": null,
      "measured_at": "2026-09-10T04:04:05Z",
      "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": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.5675354682323,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.416847410892895,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "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": 62,
      "draws": 92,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-09-10T04:44:59Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.6739310726407,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.270432377976235,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 497,
      "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": 180,
      "draws": 357,
      "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": 101,
      "max_score": null,
      "measured_at": "2026-09-10T09:52:12Z",
      "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": 497,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.9768231349922,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.22733450545151,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 54,
      "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": 27,
      "draws": 40,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-07-31T02:38:28Z",
      "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": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.4264006717276,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.037675249257887,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "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": 64,
      "draws": 53,
      "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": 42,
      "max_score": null,
      "measured_at": "2026-09-10T03:14:32Z",
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.5379926925962,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.843971005685763,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 200,
      "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": 100,
      "draws": 128,
      "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": 55,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:54Z",
      "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": 199,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.4936244989651,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.825666754280896,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 271,
      "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": 98,
      "draws": 191,
      "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": 39,
      "max_score": null,
      "measured_at": "2026-09-10T09:56:32Z",
      "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": 267,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.1765238688329,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.748427314763532,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 130,
      "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": 65,
      "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-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": "2026-09-10T07:15:52Z",
      "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": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.8661207582813,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.611947649463634,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 114,
      "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": 57,
      "draws": 85,
      "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": 21,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:17Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.061245609558,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.58598065433972,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 8
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": null,
      "draws": 77,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-07-31T02:33:25Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.0555423491355,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.529957742172513,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 28.291258434495777,
      "unilateral_faults": null,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "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": 40,
      "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-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": 15,
      "max_score": null,
      "measured_at": "2026-08-03T14:28:39Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.3238586920036,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.27457919744084,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "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": 66,
      "draws": 79,
      "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": 36,
      "max_score": null,
      "measured_at": "2026-09-10T09:57:26Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.0204773592366,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.019165184642294,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 56,
      "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": 27,
      "draws": 45,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-04T23:28:00Z",
      "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": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.4292622210753,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.87218750063355,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "draws": 96,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-09-10T07:20:36Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.9682278137316,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.743112742729135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "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": 32,
      "draws": 51,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-08-03T11:49:23Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.7140351902344,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.72518278425092,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "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": 63,
      "draws": 84,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:34Z",
      "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": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.2604001496738,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.42835891103803,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "draws": 85,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:18Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.5158485739823,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.337256754953387,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "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": 27,
      "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": "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": 7,
      "max_score": null,
      "measured_at": "2026-07-31T02:38:24Z",
      "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": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.0577329475452,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.1562199693787,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 196,
      "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": 74,
      "draws": 137,
      "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": 32,
      "max_score": null,
      "measured_at": "2026-09-10T09:54:08Z",
      "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": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.7907735203491,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 21.52240960642956,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "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": 62,
      "draws": 99,
      "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": 18,
      "max_score": null,
      "measured_at": "2026-09-10T04:42:34Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.5499543455337,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 21.436503442115733,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "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": 63,
      "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": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-09-10T09:52:42Z",
      "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": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.9495004871246,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 21.38393789540447,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 337,
      "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": 133,
      "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": "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": 35,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:54Z",
      "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": 327,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.4959236408645,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 21.30546578772129,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.640518153991441,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 140,
      "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": 70,
      "draws": 106,
      "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": 14,
      "max_score": null,
      "measured_at": "2026-09-10T07:15:44Z",
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.2741887633456,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 21.24043269755691,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 142,
      "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": 69,
      "draws": 95,
      "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": 26,
      "max_score": null,
      "measured_at": "2026-08-05T03:47:58Z",
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.689412717466,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 21.233388940349045,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.179828253878973,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "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": 59,
      "draws": 95,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-09-10T07:14:29Z",
      "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": 127,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.633225132272,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.5271127751659,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.444173824159213,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 184,
      "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": 89,
      "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": "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": 46,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:54Z",
      "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": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.112805928553,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.26667941148646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 114,
      "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": 57,
      "draws": 92,
      "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": 10,
      "max_score": null,
      "measured_at": "2026-09-10T00:27:30Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.3664247023332,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.161095610049934,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 94,
      "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": 14,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:50Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.6029710194987,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.139382489297006,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 299,
      "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": 103,
      "draws": 167,
      "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": 100,
      "max_score": null,
      "measured_at": "2026-09-10T05:30:54Z",
      "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": 299,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.3582535632365,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.028370513249424,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 116,
      "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": 57,
      "draws": 76,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:34Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.5683313615027,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 19.863520529847257,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 245,
      "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": 91,
      "draws": 138,
      "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": 79,
      "max_score": null,
      "measured_at": "2026-09-10T07:15:32Z",
      "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": 245,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.4089666754899,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 19.803571551585858,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 116,
      "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": 58,
      "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": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-09-10T05:30:59Z",
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.6673306827304,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 19.436408028603687,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "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": 30,
      "draws": 40,
      "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": 14,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:51Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.4471348945187,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 19.361118709233534,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 337,
      "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": 135,
      "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": "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": 51,
      "max_score": null,
      "measured_at": "2026-09-10T09:51:11Z",
      "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": 337,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.4671288080813,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 19.256845011483584,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.0009297552497305,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "draws": 78,
      "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": 21,
      "max_score": null,
      "measured_at": "2026-09-10T07:15:45Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.8842293634966,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 19.25382084260791,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "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": "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": 20,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:32Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.006254461214,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 19.108520570352844,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 188,
      "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": 69,
      "draws": 132,
      "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": 30,
      "max_score": null,
      "measured_at": "2026-09-10T09:49:10Z",
      "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": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.720030490479,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 19.09499131510905,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 128,
      "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": 64,
      "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": "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": 23,
      "max_score": null,
      "measured_at": "2026-09-10T04:42:36Z",
      "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": 127,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.6094997952396,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 18.70274366327956,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.444173824159213,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "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": 82,
      "draws": 187,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:59Z",
      "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": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.0682594652842,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 18.656566613036805,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 136,
      "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": 64,
      "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": "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": 32,
      "max_score": null,
      "measured_at": "2026-07-31T02:33:23Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.0163545286596,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 18.615122693395733,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.61455287691689,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "draws": 72,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:51Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.6225816346569,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 18.38304555561166,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "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": "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": 17,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:46Z",
      "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": 113,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.61860583031,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 18.355372189033734,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.079290579084697,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "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": "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": 16,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:50Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.2957587674696,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.99796849337146,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "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": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-09-10T09:48:58Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.9814194878577,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.78045219003907,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 222,
      "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": 79,
      "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": "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": 28,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:21Z",
      "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": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.148036085779,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.562136050360625,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 128,
      "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": 64,
      "draws": 106,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-09-10T07:14:15Z",
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.3850925129989,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.529864794901115,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "draws": 82,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:38Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.484902413154,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.367291620527613,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 184,
      "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": 71,
      "draws": 116,
      "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": 45,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:02Z",
      "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": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.1545682656892,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.294684637089965,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 62,
      "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": 31,
      "draws": 35,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-08-04T23:00:29Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.2086777568848,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.140349376902293,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 4
    },
    {
      "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": 203,
      "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": 39,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:54Z",
      "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": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.2708927832791,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.068321646037397,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "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": 31,
      "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": "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": 13,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:54Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.2779463608167,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 16.95013592673012,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 130,
      "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": 59,
      "draws": 103,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:22Z",
      "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": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.0555206532733,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 16.196026786301488,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 467,
      "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": 160,
      "draws": 318,
      "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": 98,
      "max_score": null,
      "measured_at": "2026-09-10T09:51:02Z",
      "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": 465,
      "rating_method": "sequential_elo",
      "raw_elo": 1397.6493104991137,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 15.758295958987606,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 62,
      "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": 31,
      "draws": 48,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-08-05T00:50:32Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.8618510492545,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 15.428003461676202,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "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": 83,
      "draws": 103,
      "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": 76,
      "max_score": null,
      "measured_at": "2026-09-10T09:49:38Z",
      "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": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1387.6702135204537,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 14.194010354631436,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 184,
      "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": 68,
      "draws": 101,
      "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": 53,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:53Z",
      "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": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1390.1989659365513,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 13.992136416293384,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 114,
      "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": 57,
      "draws": 70,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:59Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.7280216533547,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 13.104662042950768,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "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": 86,
      "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": "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": 71,
      "max_score": null,
      "measured_at": "2026-09-10T09:49:00Z",
      "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": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1368.0246720541775,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 11.01099847514966,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 114,
      "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": 57,
      "draws": 82,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-09-10T09:50:29Z",
      "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": 1378.4663573739215,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.74443090510793,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 186,
      "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": 68,
      "draws": 104,
      "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": 62,
      "max_score": null,
      "measured_at": "2026-09-10T09:52:12Z",
      "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": 186,
      "rating_method": "sequential_elo",
      "raw_elo": 1362.819635098196,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 9.48709633237125,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 114,
      "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": 57,
      "draws": 73,
      "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": 28,
      "max_score": null,
      "measured_at": "2026-09-10T09:50:49Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1369.3199862945683,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 9.230754142229273,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 114,
      "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": 57,
      "draws": 80,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-09-10T09:50:45Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1363.6054976163036,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 8.285036037313507,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 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": "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": 22,
      "max_score": null,
      "measured_at": "2026-09-10T09:52:42Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1362.1274696591013,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 8.040430110624992,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 15
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 491,
      "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": 166,
      "draws": 277,
      "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": 141,
      "max_score": null,
      "measured_at": "2026-09-10T09:51:03Z",
      "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": 458,
      "rating_method": "sequential_elo",
      "raw_elo": 1336.279199723666,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 5.565460776989309,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 33,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "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-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": 50,
      "max_score": null,
      "measured_at": "2026-09-10T09:56:32Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1313.5432809915524,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": "2026-09-10T10:39:41Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 2151.5735715815727,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 120
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": "2026-09-10T10:39:45Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 2090.9059975494283,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 95.24447704187754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 114
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:31Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 2049.821981812471,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 92.02404202093135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 107
    },
    {
      "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": 10,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:25Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 2039.1287831280288,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 91.18583886791443,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": null,
      "wins": 110
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "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": 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-5.4",
        "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": 22,
      "max_score": null,
      "measured_at": "2026-09-10T10:38:59Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 2022.8237873577302,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 90.58932194330986,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 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": 10,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:43Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 2014.1772003359092,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 89.2299699098686,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": null,
      "wins": 110
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 133,
      "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": 64,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:05Z",
      "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": 133,
      "rating_method": "sequential_elo",
      "raw_elo": 2006.4991720318374,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 88.76990902930297,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 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": 17,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:29Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 2007.3708129337665,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 88.69644055635243,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": null,
      "wins": 103
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 10,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:27Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1992.4645295287164,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 87.52798814855652,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 484,
      "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": 175,
      "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": 85,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:07Z",
      "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": 484,
      "rating_method": "sequential_elo",
      "raw_elo": 1930.7302324494935,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 83.5278688201069,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 399
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:06Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1928.1615545368238,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 82.4874985834472,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 98
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 156,
      "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": 78,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-08-05T04:56:12Z",
      "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": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1918.6883869209828,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 81.06683069976471,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.51792189268726,
      "unilateral_faults": 0,
      "wins": 143
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 98,
      "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": 44,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-08-03T14:57:20Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1884.381955867567,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 77.46597085447985,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.056388861645896,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "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": 30,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-08-05T01:40:01Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1871.4415622354468,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 77.00277079448404,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 53
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 154,
      "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": 77,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-08-05T05:35:16Z",
      "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": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1864.477227519094,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 76.79549207854782,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.867341638060083,
      "unilateral_faults": 0,
      "wins": 134
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "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": 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-5.6-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": 58,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:05Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1841.9988908139892,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 76.41507877251388,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 208,
      "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": 82,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:27Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1818.8623378508958,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 74.60148377480539,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 120,
      "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": 60,
      "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": 31,
      "max_score": null,
      "measured_at": "2026-09-10T10:38:56Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1820.235845616354,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 74.02757258952171,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 524,
      "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": 198,
      "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": 141,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:25Z",
      "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": 524,
      "rating_method": "sequential_elo",
      "raw_elo": 1790.0700567199,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 72.57999142955795,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 383
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "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": 90,
      "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": 72,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:07Z",
      "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": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1784.876545788455,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 72.09489879437513,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 120,
      "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": 60,
      "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": 45,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:13Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1788.349704659587,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 71.52812741168269,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 46,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:23Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1738.35460515231,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 67.60918311081942,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 48,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:16Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1737.7777429081157,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 67.56396485889975,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "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": 41,
      "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": 37,
      "max_score": null,
      "measured_at": "2026-08-05T05:34:43Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1718.4606854659032,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 65.57660382357807,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 206,
      "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": 88,
      "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": 60,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:07Z",
      "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": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1696.766819796055,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 65.02038273879721,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 120,
      "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": 60,
      "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": 61,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:42Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1670.208226339689,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 62.26742230817677,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "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": 33,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-08-05T04:43:10Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1681.0811589466743,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 62.139557449757454,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "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": 67,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:42Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1660.04663503317,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 61.62273404542139,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 120,
      "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": 60,
      "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": 62,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:46Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1660.6856082501972,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 61.52097695135376,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "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": 46,
      "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": 48,
      "max_score": null,
      "measured_at": "2026-08-05T03:48:47Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1657.1023897142595,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 60.93926279553979,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "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": 31,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-03T14:20:34Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1666.6931780509783,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 60.89199866384945,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "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": 35,
      "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": 28,
      "max_score": null,
      "measured_at": "2026-08-05T03:41:12Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1661.473206220661,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 60.71202505477096,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 57,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:24Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1641.3522369713987,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 60.00550031591886,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "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": 44,
      "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": 31,
      "max_score": null,
      "measured_at": "2026-08-04T21:09:49Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1643.1446974256544,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 59.672841954852146,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 59,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:33Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1630.175690041946,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 59.12940915250124,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "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": 30,
      "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": 29,
      "max_score": null,
      "measured_at": "2026-08-03T08:44:47Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1639.2073900533328,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 58.73748205542807,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 33
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "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": "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": 46,
      "max_score": null,
      "measured_at": "2026-07-31T03:32:24Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1636.6347907936715,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 58.364933687116554,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.9692131063861,
      "unilateral_faults": null,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 65,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:10Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1617.4113539089935,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 58.12885664164453,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 55,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:35Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1612.1526564637534,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 57.716645393220304,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "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": 29,
      "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": 31,
      "max_score": null,
      "measured_at": "2026-08-04T22:34:38Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1623.0296620496733,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 57.46936546828877,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "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": 39,
      "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": 30,
      "max_score": null,
      "measured_at": "2026-08-03T10:29:27Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1615.986901751882,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 57.33994820345935,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "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": 31,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-07-31T02:29:42Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1621.0647466868909,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 57.3153424952665,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 38
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 386,
      "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": 193,
      "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": 221,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:34Z",
      "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": 386,
      "rating_method": "sequential_elo",
      "raw_elo": 1603.5972040555732,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 57.13595607705878,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.0126757293056905,
      "unilateral_faults": 0,
      "wins": 165
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "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": 46,
      "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": 45,
      "max_score": null,
      "measured_at": "2026-08-05T03:57:18Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1608.0684118194988,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 57.095657519959566,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 214,
      "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": 90,
      "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": 112,
      "max_score": null,
      "measured_at": "2026-09-09T22:57:25Z",
      "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": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1582.1244495483195,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 56.074890123705295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 120,
      "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": 60,
      "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": 61,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:15Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1586.236607414437,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.68517523467149,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 335,
      "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": 127,
      "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": 154,
      "max_score": null,
      "measured_at": "2026-09-10T10:38:53Z",
      "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": 335,
      "rating_method": "sequential_elo",
      "raw_elo": 1571.0784225753098,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.636862652973036,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 181
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 46,
      "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": 40,
      "max_score": null,
      "measured_at": "2026-08-05T03:49:27Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1589.0366798457355,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.57150390760981,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "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": 41,
      "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": 40,
      "max_score": null,
      "measured_at": "2026-08-05T05:26:21Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1589.1184862164962,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.31987902290327,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "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": 67,
      "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": 74,
      "max_score": null,
      "measured_at": "2026-09-10T07:08:52Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1578.0415953119314,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.194640367743276,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 90,
      "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": 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": "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": 37,
      "max_score": null,
      "measured_at": "2026-08-05T04:51:41Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1579.92232517005,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.753782941211256,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "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": 67,
      "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": 80,
      "max_score": null,
      "measured_at": "2026-09-10T04:38:48Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1569.950754355836,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.56042710751232,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 264,
      "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": 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": "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": 138,
      "max_score": null,
      "measured_at": "2026-09-10T07:11:36Z",
      "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": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1554.5881102767514,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.128679364952525,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 152,
      "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": 76,
      "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": 55,
      "max_score": null,
      "measured_at": "2026-08-05T00:20:24Z",
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1575.3504369194993,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.10090278289114,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.360606452268916,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 274,
      "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": 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-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": 124,
      "max_score": null,
      "measured_at": "2026-09-10T05:24:11Z",
      "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": 274,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.897963944819,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.03153887048955,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 122,
      "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": 61,
      "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": 76,
      "max_score": null,
      "measured_at": "2026-09-10T04:38:49Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1563.9688531542206,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.96295151563907,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 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-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": 39,
      "max_score": null,
      "measured_at": "2026-08-05T02:08:36Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.90982985875,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.75866949290433,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 130,
      "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": 65,
      "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": 72,
      "max_score": null,
      "measured_at": "2026-09-10T03:37:24Z",
      "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": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.3761215959112,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.690628075980555,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 102,
      "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": 48,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-08-05T03:00:43Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1560.9179428825034,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.46148943250204,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "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": 92,
      "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": 131,
      "max_score": null,
      "measured_at": "2026-09-10T03:56:59Z",
      "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": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.8020800815002,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.37102488938938,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 54,
      "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": 27,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-07-31T00:59:23Z",
      "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": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1573.5323354052068,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.31189451791979,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 140,
      "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": 70,
      "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": 80,
      "max_score": null,
      "measured_at": "2026-09-10T10:25:33Z",
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.5287428396603,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.252816096613515,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 316,
      "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": 107,
      "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": 131,
      "max_score": null,
      "measured_at": "2026-09-10T07:08:46Z",
      "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": 316,
      "rating_method": "sequential_elo",
      "raw_elo": 1533.0248082619837,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 52.6034542376244,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 330,
      "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": 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": "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": 151,
      "max_score": null,
      "measured_at": "2026-09-10T08:08:59Z",
      "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": 330,
      "rating_method": "sequential_elo",
      "raw_elo": 1532.290670637824,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 52.5835528465637,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 156,
      "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": 78,
      "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": 84,
      "max_score": null,
      "measured_at": "2026-09-10T07:13:19Z",
      "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": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.1713370273924,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 51.56007348257478,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 120,
      "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": 60,
      "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": 70,
      "max_score": null,
      "measured_at": "2026-09-09T23:37:21Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1533.0356527584136,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 51.51493494903386,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 210,
      "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": 87,
      "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": 109,
      "max_score": null,
      "measured_at": "2026-09-10T02:54:14Z",
      "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": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.290997711097,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 51.4429639826475,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 142,
      "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": 71,
      "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": 93,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:35Z",
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.1371889267225,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 51.28098961805589,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 140,
      "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": 70,
      "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": 80,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:46Z",
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.634012263492,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.98785731400378,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 144,
      "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": 72,
      "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": 91,
      "max_score": null,
      "measured_at": "2026-09-10T04:38:47Z",
      "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": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.2842748535527,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.68357221574452,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 156,
      "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": 77,
      "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": 72,
      "max_score": null,
      "measured_at": "2026-08-05T04:42:37Z",
      "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": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1530.8163667007361,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.607779083394135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.396498219564457,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 46,
      "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": 46,
      "max_score": null,
      "measured_at": "2026-08-03T14:57:20Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1526.3767034116547,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.59206002860415,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "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": 66,
      "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": 71,
      "max_score": null,
      "measured_at": "2026-09-10T08:14:45Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.1130671086878,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.555220904982725,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 78,
      "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": 39,
      "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": 36,
      "max_score": null,
      "measured_at": "2026-08-05T01:37:44Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.1416526227213,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.37567398128637,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "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": 67,
      "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": 78,
      "max_score": null,
      "measured_at": "2026-09-10T08:08:17Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.4033276853204,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.36302806951727,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 80,
      "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": 40,
      "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": 38,
      "max_score": null,
      "measured_at": "2026-08-03T11:29:18Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.644299345217,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.1453521622104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "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": 46,
      "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": 48,
      "max_score": null,
      "measured_at": "2026-08-05T02:51:39Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.1946829738897,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.98510602874532,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "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": 41,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-08-04T23:21:58Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.989498345392,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.97948143649212,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 38
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 1035,
      "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": 360,
      "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": 499,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:46Z",
      "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": 1035,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.3768543058302,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.93788221593318,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 536
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "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": 33,
      "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": 31,
      "max_score": null,
      "measured_at": "2026-08-05T03:40:34Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.5004355757312,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.787345255628644,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 51,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-08-04T22:17:40Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1513.5433220252949,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.77752038298693,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 170,
      "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": 85,
      "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": 89,
      "max_score": null,
      "measured_at": "2026-09-10T05:28:37Z",
      "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": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.4193979704903,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.72447731658255,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 122,
      "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": 61,
      "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": 50,
      "max_score": null,
      "measured_at": "2026-09-10T08:08:18Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.2863092900893,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.36302826110043,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 388,
      "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": 194,
      "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": 174,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:39Z",
      "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": 388,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.461141249657,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.214171810132676,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.0126757293056905,
      "unilateral_faults": 0,
      "wins": 214
    },
    {
      "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": 44,
      "max_score": null,
      "measured_at": "2026-08-05T02:08:01Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.461307692719,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.11080098947388,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.824399540348086,
      "unilateral_faults": null,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "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": 67,
      "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": 82,
      "max_score": null,
      "measured_at": "2026-09-10T05:26:53Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.4448278723703,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.03370945933072,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 148,
      "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": 74,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:07Z",
      "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": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.9428710696504,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.96749514971631,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 162,
      "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": 81,
      "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": 77,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:31Z",
      "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": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.4990644868933,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.81033417432173,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 142,
      "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": 71,
      "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": 53,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:13Z",
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.6092653665523,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.574464166754886,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 176,
      "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": 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": "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": 88,
      "max_score": null,
      "measured_at": "2026-09-10T10:38:57Z",
      "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": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.3395710789268,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.348251895031375,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 288,
      "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": 90,
      "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": 140,
      "max_score": null,
      "measured_at": "2026-09-10T05:23:34Z",
      "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": 288,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.1401355707098,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.82596170566252,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 154,
      "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": 71,
      "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": 71,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:26Z",
      "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": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.6810024880726,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.821376524556854,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 136,
      "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": 68,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-09-10T05:27:40Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.0833874264852,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.45741606820675,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 144,
      "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": 70,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-08-05T00:09:03Z",
      "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": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.012787457223,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.23542996577578,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.919558612226904,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 118,
      "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": 59,
      "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": 61,
      "max_score": null,
      "measured_at": "2026-07-31T03:34:44Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.8310415559054,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.95690988688564,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.633827169132047,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 635,
      "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": 219,
      "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": 291,
      "max_score": null,
      "measured_at": "2026-09-10T07:12:26Z",
      "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": 635,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.5951989347143,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.84746789517817,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 344
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 164,
      "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": 82,
      "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": 62,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:33Z",
      "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": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.1691456804797,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.761351709774466,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 90,
      "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": 45,
      "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": 46,
      "max_score": null,
      "measured_at": "2026-08-03T11:38:28Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.8637902645755,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.440218311437484,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 164,
      "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": 82,
      "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": 95,
      "max_score": null,
      "measured_at": "2026-09-10T08:06:46Z",
      "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": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.4581407186583,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.686593077752605,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 220,
      "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": 82,
      "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": 91,
      "max_score": null,
      "measured_at": "2026-09-10T07:11:12Z",
      "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": 220,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.8378450569335,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.42107820004769,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 267,
      "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": 93,
      "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": 122,
      "max_score": null,
      "measured_at": "2026-09-10T04:38:52Z",
      "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": 267,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.2585433768318,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.41274737025844,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 146,
      "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": 73,
      "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": 55,
      "max_score": null,
      "measured_at": "2026-09-10T06:05:41Z",
      "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": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.2778157227672,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.29216666489487,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 230,
      "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": 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-5.6-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": 80,
      "max_score": null,
      "measured_at": "2026-09-10T05:27:35Z",
      "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": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.999852136446,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.24477513071418,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 207,
      "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": 80,
      "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": 99,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:13Z",
      "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": 207,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.6706022597677,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.951124002900116,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 120,
      "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": 60,
      "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": 43,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:01Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.3534727627618,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.64182972536665,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "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": 37,
      "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": 31,
      "max_score": null,
      "measured_at": "2026-08-03T10:09:34Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.3115832325407,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.46448138749022,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 57,
      "max_score": null,
      "measured_at": "2026-09-10T10:25:56Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.1675043060943,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.07854631545282,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "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": 64,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-09-10T07:08:54Z",
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.282174092201,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.86378827356518,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "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": 39,
      "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": 38,
      "max_score": null,
      "measured_at": "2026-08-03T14:20:21Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.9499590147173,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.46262973385445,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 3,
      "attempted_matches": 406,
      "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": 203,
      "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": 198,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:22Z",
      "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": 406,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.8517046947445,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.3483500632467,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.5681818181818196,
      "unilateral_faults": 0,
      "wins": 208
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "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": 67,
      "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": 54,
      "max_score": null,
      "measured_at": "2026-09-10T08:06:59Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.7633280592884,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.17968294559612,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 78,
      "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": 39,
      "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": 37,
      "max_score": null,
      "measured_at": "2026-08-03T12:50:04Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.8923348583521,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.90940679325011,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 41
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 562,
      "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": 192,
      "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": 345,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:01Z",
      "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": 562,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.9234581653127,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.612280911763705,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 139,
      "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": 65,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-09-09T21:24:45Z",
      "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": 139,
      "rating_method": "sequential_elo",
      "raw_elo": 1412.0945828140425,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.23525046231568,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 86,
      "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": 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": "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": 49,
      "max_score": null,
      "measured_at": "2026-07-31T03:33:36Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.9405691439395,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.21703774485679,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "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": 63,
      "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": 50,
      "max_score": null,
      "measured_at": "2026-09-10T04:39:18Z",
      "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": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1412.4135684859086,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.1279310571795,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 57,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:26Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1383.0705290094131,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.75968347765998,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-09-10T05:24:36Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1374.7864842662034,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.11032563550241,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 132,
      "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": 66,
      "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": 72,
      "max_score": null,
      "measured_at": "2026-07-31T03:33:39Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1385.9981373711466,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.00901191465739,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "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": 85,
      "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": 158,
      "max_score": null,
      "measured_at": "2026-09-10T03:41:09Z",
      "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": 1349.1837565795022,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.997988417921604,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 82,
      "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": 41,
      "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": 48,
      "max_score": null,
      "measured_at": "2026-08-05T04:56:04Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1362.0329257769195,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.51942114475686,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "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": 42,
      "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": 56,
      "max_score": null,
      "measured_at": "2026-08-04T09:17:51Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1328.357377257976,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.95975901608025,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 30
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 174,
      "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": 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": "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": 107,
      "max_score": null,
      "measured_at": "2026-08-05T01:30:14Z",
      "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": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1327.4143578677654,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.903535425620994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.573428145379982,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 44,
      "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": 59,
      "max_score": null,
      "measured_at": "2026-08-05T03:42:02Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1322.9127343144567,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.643217642393346,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 33
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 134,
      "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": 67,
      "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": 80,
      "max_score": null,
      "measured_at": "2026-07-31T02:29:43Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1314.6556809127424,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.4446834720705,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.888824360518605,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 581,
      "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": 195,
      "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": 373,
      "max_score": null,
      "measured_at": "2026-09-10T10:38:59Z",
      "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": 581,
      "rating_method": "sequential_elo",
      "raw_elo": 1273.9436592054853,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.2189735823991,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 74,
      "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": 37,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-08-05T03:40:16Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1295.479782930378,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.123645602053834,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 88,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:04Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1267.6313790429688,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.71080462121027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "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": 55,
      "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": 70,
      "max_score": null,
      "measured_at": "2026-08-05T04:51:41Z",
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1258.6306450543475,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.879639110693958,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 206,
      "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": 77,
      "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": 135,
      "max_score": null,
      "measured_at": "2026-09-10T10:38:51Z",
      "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": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1244.6897025475216,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.583608741898452,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 78,
      "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": 39,
      "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": 53,
      "max_score": null,
      "measured_at": "2026-08-04T21:09:30Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1241.5251670106486,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.987177717585375,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 60,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:03Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1217.9429183062275,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.815896681391532,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "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": 38,
      "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": 50,
      "max_score": null,
      "measured_at": "2026-08-05T03:40:43Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1222.6598405913285,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.4628692919667,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "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": 37,
      "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": 51,
      "max_score": null,
      "measured_at": "2026-08-05T02:32:27Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1201.6240382292942,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.766615824644276,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 206,
      "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": 76,
      "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": 137,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:04Z",
      "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": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1180.4517267849226,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.54821424333988,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 66,
      "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": 32,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-08-05T00:53:07Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1197.5672854163643,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.238563997706606,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 142,
      "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": 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-5.4-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": 109,
      "max_score": null,
      "measured_at": "2026-08-05T04:56:12Z",
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1193.9987947074715,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.093974048156653,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.179828253878973,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "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": 31,
      "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": 48,
      "max_score": null,
      "measured_at": "2026-07-31T03:34:49Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1192.492164384378,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.721008341051526,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 120,
      "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": 60,
      "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": 90,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:06Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1174.9076097253715,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.442506509935026,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 89,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:03Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1162.6706570017993,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.483293774914944,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 508,
      "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": 162,
      "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": 372,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:00Z",
      "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": 508,
      "rating_method": "sequential_elo",
      "raw_elo": 1140.5555835818523,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 21.63668679667324,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 158,
      "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": 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": "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": 111,
      "max_score": null,
      "measured_at": "2026-08-03T22:34:39Z",
      "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": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1142.237542324819,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.179848697832213,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.895291237259062,
      "unilateral_faults": 4,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 89,
      "max_score": null,
      "measured_at": "2026-09-10T10:38:57Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1131.9752508173779,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.07718621008026,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 522,
      "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": 170,
      "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": 405,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:06Z",
      "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": 522,
      "rating_method": "sequential_elo",
      "raw_elo": 1078.209332432158,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 16.775466878832237,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 120,
      "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": 60,
      "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": 90,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:05Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1076.3642382857881,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 15.718029757272555,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 542,
      "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": 182,
      "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": 426,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:05Z",
      "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": 542,
      "rating_method": "sequential_elo",
      "raw_elo": 1062.4837451299554,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 15.579243027156668,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 120,
      "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": 60,
      "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": 94,
      "max_score": null,
      "measured_at": "2026-09-10T10:38:52Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1066.7098759830644,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 14.961257423631709,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 90,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:06Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1048.5046266155819,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 13.534210393870193,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 97,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:26Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1017.3234430605204,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 11.090024407811828,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "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": 62,
      "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": 116,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:33Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1009.4016134129805,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.600689036218679,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 544,
      "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": 184,
      "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": 464,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:33Z",
      "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": 544,
      "rating_method": "sequential_elo",
      "raw_elo": 993.6783536394931,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.189281084335075,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 120,
      "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": 60,
      "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": 106,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:27Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 965.0191901221987,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 6.990073492948425,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "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": 42,
      "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": 86,
      "max_score": null,
      "measured_at": "2026-08-04T23:59:53Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 946.7487485340107,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 5.046768034226976,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "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": 62,
      "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": 128,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:15Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 873.907694545383,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 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": 6,
      "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": 1,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:07Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 2147.0653496170057,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 111
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 11,
      "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": 7,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:04Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 2093.753980134374,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 95.8308881823799,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 100
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 14,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-09-10T10:25:56Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 2026.885219432552,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 90.60154698973984,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 93
    },
    {
      "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": 11,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-09-10T10:09:30Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1991.6471169850581,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 87.8458198199057,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 85
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 11,
      "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": 21,
      "max_score": null,
      "measured_at": "2026-09-10T10:08:55Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1966.5752403122613,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 85.88512253636422,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 508,
      "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": 185,
      "draws": 26,
      "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": 107,
      "max_score": null,
      "measured_at": "2026-09-10T10:15:27Z",
      "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": 508,
      "rating_method": "sequential_elo",
      "raw_elo": 1951.3393726264744,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 85.6020891745296,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 206,
      "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": 84,
      "draws": 24,
      "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": 25,
      "max_score": null,
      "measured_at": "2026-09-10T10:10:09Z",
      "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": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1949.7197444262995,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 85.26032097966694,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 212,
      "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": 86,
      "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-5.4",
        "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": 40,
      "max_score": null,
      "measured_at": "2026-09-10T09:59:54Z",
      "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": 212,
      "rating_method": "sequential_elo",
      "raw_elo": 1877.695734805393,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 79.65866479600288,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 118,
      "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": 59,
      "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": "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": 26,
      "max_score": null,
      "measured_at": "2026-09-10T10:10:15Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1886.2027783372537,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 79.59975068636147,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 14,
      "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": 25,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:13Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1885.758929737167,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 79.56504037106075,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "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": 33,
      "draws": 3,
      "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": 3,
      "max_score": null,
      "measured_at": "2026-08-03T09:47:39Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1897.0527582969269,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 79.49418767823046,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 206,
      "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": 85,
      "draws": 34,
      "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": 38,
      "max_score": null,
      "measured_at": "2026-09-10T10:05:47Z",
      "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": 205,
      "rating_method": "sequential_elo",
      "raw_elo": 1871.2923877720345,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 79.12179151899733,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 118,
      "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": 59,
      "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": "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": 26,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:07Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1867.8354878191371,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 78.16337250474885,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 512,
      "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": 189,
      "draws": 51,
      "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": 81,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:25Z",
      "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": 512,
      "rating_method": "sequential_elo",
      "raw_elo": 1850.8283392924154,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 77.74963744928857,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 118,
      "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": 59,
      "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": "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": 30,
      "max_score": null,
      "measured_at": "2026-09-10T10:05:14Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1854.3315939739264,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 77.10732678766597,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 8,
      "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": 39,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:12Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1849.1694453365888,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 76.70363100762701,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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": "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": 39,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:17Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1837.9129732888766,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 75.82334053498934,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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-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": 40,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:18Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1836.2178346014025,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 75.69077551550029,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "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": 15,
      "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": 31,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:54Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1832.4555169206908,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 75.39655078902038,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 10,
      "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": 21,
      "max_score": null,
      "measured_at": "2026-09-10T10:02:31Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1817.90041052838,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 74.25829704210302,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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": "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": 37,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:22Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1817.3175803869053,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 74.21271794604775,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 16,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:33Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1817.1444184138888,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 74.19917615120977,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "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": 22,
      "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-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": 6,
      "max_score": null,
      "measured_at": "2026-08-03T14:42:32Z",
      "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": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1837.2193099629035,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 73.97350967200747,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 30.785599249992988,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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-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": 38,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:50Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1811.6841955171515,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 73.77217005426371,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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": "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": 40,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:49Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1806.1969162678647,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 73.34304806796328,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 6,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-09-10T10:02:00Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1802.9206210982431,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 73.08683178535341,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 16,
      "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": 26,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:00Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1801.5308334075144,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 72.97814614584291,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 18,
      "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": 37,
      "max_score": null,
      "measured_at": "2026-09-10T10:00:07Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1797.2725457387294,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 72.64513505242988,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 24,
      "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": 32,
      "max_score": null,
      "measured_at": "2026-09-10T10:01:12Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1790.8162168118583,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 72.14023042347958,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "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": 31,
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T07:40:51Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1789.1763903140825,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 70.99957787144118,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "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": 85,
      "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-5.4",
        "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": 52,
      "max_score": null,
      "measured_at": "2026-09-10T09:56:14Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1766.52793989414,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 70.9445905573761,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 140
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "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": 19,
      "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-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": 5,
      "max_score": null,
      "measured_at": "2026-08-03T10:32:38Z",
      "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": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1799.4148654160863,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 70.79490986212144,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 14,
      "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": 42,
      "max_score": null,
      "measured_at": "2026-09-10T09:58:52Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1771.5461514507922,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 70.6332524935784,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "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": 30,
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T08:42:55Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1783.9848192621998,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 70.46838917607434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "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": 35,
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T05:25:24Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1773.266695390409,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 70.02330483752023,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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": "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": 56,
      "max_score": null,
      "measured_at": "2026-09-10T10:00:40Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1757.9430530119864,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 69.56944867447089,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 17,
      "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": 38,
      "max_score": null,
      "measured_at": "2026-09-10T09:59:53Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1756.280219142349,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 69.43940999034174,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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": "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": 51,
      "max_score": null,
      "measured_at": "2026-09-10T10:00:11Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1752.85806974237,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 69.17178746172216,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "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": 22,
      "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": "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": 10,
      "max_score": null,
      "measured_at": "2026-07-30T23:51:19Z",
      "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": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1736.7735012984654,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 66.11834084034295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 30.785599249992988,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "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": 26,
      "draws": 3,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-08-03T13:30:44Z",
      "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": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1723.3452380747874,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 65.51337979360243,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "draws": 10,
      "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": 45,
      "max_score": null,
      "measured_at": "2026-09-10T05:40:23Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1688.7833998028116,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 64.18475015909165,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 408,
      "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": 194,
      "draws": 62,
      "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": 119,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:32Z",
      "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": 408,
      "rating_method": "sequential_elo",
      "raw_elo": 1675.6494431146332,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 63.32717677815119,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 1,
      "attempted_matches": 230,
      "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": 90,
      "draws": 17,
      "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": 90,
      "max_score": null,
      "measured_at": "2026-09-10T01:40:11Z",
      "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": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1629.395387453824,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 60.326020445609515,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 158,
      "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": 78,
      "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-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": 52,
      "max_score": null,
      "measured_at": "2026-08-05T06:55:07Z",
      "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": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1644.7113224940283,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 60.07944202124918,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.233820686813306,
      "unilateral_faults": 0,
      "wins": 102
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 332,
      "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": 118,
      "draws": 32,
      "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": 165,
      "max_score": null,
      "measured_at": "2026-09-10T05:52:53Z",
      "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": 332,
      "rating_method": "sequential_elo",
      "raw_elo": 1621.172337112724,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 60.02690569508898,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 86,
      "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": 41,
      "draws": 10,
      "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": 25,
      "max_score": null,
      "measured_at": "2026-08-05T05:35:11Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1629.0069225523212,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 59.000095631169074,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "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": 37,
      "draws": 7,
      "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": 26,
      "max_score": null,
      "measured_at": "2026-08-05T03:41:43Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1630.394611108272,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 58.942903698869344,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "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": 69,
      "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": "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": 69,
      "max_score": null,
      "measured_at": "2026-09-10T03:21:43Z",
      "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": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1618.5910337917292,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 58.886001713839136,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 142,
      "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": 71,
      "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": "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": 88,
      "max_score": null,
      "measured_at": "2026-09-10T02:27:04Z",
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1610.3425038521104,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 58.27831291867289,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 82,
      "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": 40,
      "draws": 8,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-08-05T03:57:23Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1620.6162562438012,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 58.26405875417527,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 47
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 106,
      "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": 53,
      "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": "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": 38,
      "max_score": null,
      "measured_at": "2026-07-31T20:22:51Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1628.3438282033812,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 57.999842290797865,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 25.014839042432094,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "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": 41,
      "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",
        "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": 29,
      "max_score": null,
      "measured_at": "2026-08-05T05:03:53Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1601.8729234393843,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 56.83890819619163,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "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": 42,
      "draws": 10,
      "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": 30,
      "max_score": null,
      "measured_at": "2026-08-05T01:53:50Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1591.3433947162612,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 56.015466910410275,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "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": 38,
      "draws": 9,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-08-03T13:58:04Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1591.8487355395282,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.88308492443146,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:xiaomi-mimo-v2-5:024b37c390436d5a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "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": "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": 26,
      "max_score": null,
      "measured_at": "2026-07-31T20:22:54Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1597.443682966158,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.88030293196678,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 318,
      "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": 103,
      "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": "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": 116,
      "max_score": null,
      "measured_at": "2026-09-10T07:35:06Z",
      "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": 318,
      "rating_method": "sequential_elo",
      "raw_elo": 1567.1387534647272,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.764102739590896,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 566,
      "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": 195,
      "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-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": 272,
      "max_score": null,
      "measured_at": "2026-09-10T01:44:23Z",
      "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": 566,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.7066470450266,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.547243139429334,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 320,
      "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": 107,
      "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": 152,
      "max_score": null,
      "measured_at": "2026-09-10T10:25:37Z",
      "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": 320,
      "rating_method": "sequential_elo",
      "raw_elo": 1561.5618918252717,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.3334397747058,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 308,
      "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": 101,
      "draws": 28,
      "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": 132,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:43Z",
      "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": 308,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.7762840301411,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.59615975953049,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 136,
      "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": 68,
      "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": "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": 74,
      "max_score": null,
      "measured_at": "2026-09-10T06:18:24Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.0003438184813,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.268094704811084,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 160,
      "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": 74,
      "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": "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": 84,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:07Z",
      "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": 160,
      "rating_method": "sequential_elo",
      "raw_elo": 1543.9232121385512,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.23468310597876,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 66,
      "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": 33,
      "draws": 8,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-08-05T01:59:52Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1558.851644552222,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.0458282808096,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 176,
      "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": 88,
      "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": "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": 101,
      "max_score": null,
      "measured_at": "2026-09-10T09:56:14Z",
      "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": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.6481680538632,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.0144266368767,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": null,
      "draws": 8,
      "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": 58,
      "max_score": null,
      "measured_at": "2026-07-31T20:22:43Z",
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.9617638637314,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 52.88002795050282,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.37252890985009,
      "unilateral_faults": null,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 158,
      "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": 79,
      "draws": 4,
      "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": 88,
      "max_score": null,
      "measured_at": "2026-09-10T07:29:21Z",
      "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": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.5551640009767,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 52.643022639184814,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 164,
      "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": 82,
      "draws": 10,
      "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": 68,
      "max_score": null,
      "measured_at": "2026-09-10T10:09:30Z",
      "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": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1532.4239830449544,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 52.36547411825162,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 116,
      "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": 58,
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T20:23:03Z",
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1553.24870701179,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 52.34975966070658,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.45703254059771,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 156,
      "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": 78,
      "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": "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": 80,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:25Z",
      "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": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.1409844045036,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 52.04746013492715,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 232,
      "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": 87,
      "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-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": 108,
      "max_score": null,
      "measured_at": "2026-09-10T09:59:54Z",
      "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": 231,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.7437375270322,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 51.75536719315471,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 114
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 251,
      "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": 90,
      "draws": 7,
      "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": 110,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:32Z",
      "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": 251,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.5430167446611,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 51.74464823357423,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 140,
      "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": 68,
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:41:10Z",
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.7984680553782,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 51.6471832448803,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.8742369405862,
      "unilateral_faults": 0,
      "wins": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 177,
      "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": 85,
      "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": "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": 103,
      "max_score": null,
      "measured_at": "2026-09-10T07:37:36Z",
      "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": 177,
      "rating_method": "sequential_elo",
      "raw_elo": 1513.006229205502,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.937559609413256,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 168,
      "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": 84,
      "draws": 7,
      "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": 81,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:24Z",
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.7368874771566,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.69846903136761,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 288,
      "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": 89,
      "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": "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": 114,
      "max_score": null,
      "measured_at": "2026-09-10T10:15:29Z",
      "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": 288,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.4476857106802,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.694607148650334,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 326,
      "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": 109,
      "draws": 29,
      "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": 155,
      "max_score": null,
      "measured_at": "2026-09-10T10:09:09Z",
      "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": 326,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.2475127581479,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.63276325737119,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 146,
      "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": 73,
      "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": "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": 87,
      "max_score": null,
      "measured_at": "2026-09-10T07:32:19Z",
      "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": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.241400953843,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.3128908338914,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 156,
      "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": 73,
      "draws": 4,
      "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": 51,
      "max_score": null,
      "measured_at": "2026-09-10T06:18:39Z",
      "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": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.2457744100418,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.240345149208736,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 323,
      "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": 106,
      "draws": 30,
      "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": 142,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:13Z",
      "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": 323,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.4668228591477,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.68684753126993,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 100,
      "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": 49,
      "draws": 1,
      "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": 55,
      "max_score": null,
      "measured_at": "2026-08-03T09:49:28Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.4542538973014,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.5623612264452,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 168,
      "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": 84,
      "draws": 6,
      "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": 64,
      "max_score": null,
      "measured_at": "2026-09-10T00:52:26Z",
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.8854983078986,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.129390124936364,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 202,
      "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": 101,
      "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": "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": 92,
      "max_score": null,
      "measured_at": "2026-09-10T06:16:55Z",
      "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": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.6613947942544,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.009788801136246,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 118,
      "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": 59,
      "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": 45,
      "max_score": null,
      "measured_at": "2026-09-10T09:44:31Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.0349225157022,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.91438765370183,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 312,
      "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": 104,
      "draws": 24,
      "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": 132,
      "max_score": null,
      "measured_at": "2026-09-10T05:33:33Z",
      "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": 312,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.074893914877,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.765690377579354,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 72,
      "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": 36,
      "draws": 5,
      "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": 32,
      "max_score": null,
      "measured_at": "2026-08-05T03:20:38Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.9694663520272,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.6630449859877,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 146,
      "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": 73,
      "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-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": 65,
      "max_score": null,
      "measured_at": "2026-09-10T07:31:24Z",
      "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": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.3776071905042,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.66463879800661,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 148,
      "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": 74,
      "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": "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": 53,
      "max_score": null,
      "measured_at": "2026-09-10T04:47:52Z",
      "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": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.1515439087545,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.3515218979427,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 74,
      "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": 36,
      "draws": 2,
      "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": 40,
      "max_score": null,
      "measured_at": "2026-08-05T00:01:30Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.2172455852156,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.69828843610223,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 146,
      "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": 73,
      "draws": 11,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-09-10T07:23:54Z",
      "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": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.7153447051658,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.2051929082044,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 184,
      "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": 90,
      "draws": 16,
      "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": 90,
      "max_score": null,
      "measured_at": "2026-08-05T04:32:58Z",
      "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": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.3276839958567,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.89316223345493,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.242236982581751,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "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": 83,
      "draws": 14,
      "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": 96,
      "max_score": null,
      "measured_at": "2026-09-10T09:57:11Z",
      "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": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.0180595611305,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.742957151306456,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 134,
      "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": 67,
      "draws": 7,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-09-10T02:26:59Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.156962894926,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.876252741029056,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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:GB2-06: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": 50,
      "draws": 7,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-08-05T04:57:37Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.2718722969803,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.7593724232428,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 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": "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": 53,
      "max_score": null,
      "measured_at": "2026-08-03T12:10:00Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.1758902452225,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.47206803669905,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "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": 68,
      "draws": 9,
      "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": 56,
      "max_score": null,
      "measured_at": "2026-09-10T01:43:49Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.0307512062466,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.41688806132841,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 80,
      "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": 40,
      "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": "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": 37,
      "max_score": null,
      "measured_at": "2026-08-03T09:47:39Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.373702874258,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.26617619713358,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 42
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 1137,
      "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": 366,
      "draws": 30,
      "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": 541,
      "max_score": null,
      "measured_at": "2026-09-10T10:09:06Z",
      "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": 1137,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.9750860855493,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.97644177549341,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 566
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "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": 51,
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T10:58:16Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.4761224416814,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.02538255150319,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 39
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 450,
      "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": 211,
      "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": "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": 267,
      "max_score": null,
      "measured_at": "2026-09-10T10:15:27Z",
      "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": 450,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.3196759557468,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.75760836120296,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 560,
      "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": 186,
      "draws": 25,
      "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": 293,
      "max_score": null,
      "measured_at": "2026-09-10T10:05:14Z",
      "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": 560,
      "rating_method": "sequential_elo",
      "raw_elo": 1386.774966776137,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.536391992160105,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 242
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "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": 64,
      "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": 58,
      "max_score": null,
      "measured_at": "2026-09-10T04:04:06Z",
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1397.6542566136736,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.50715196387154,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "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": 69,
      "draws": 16,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-09-10T02:26:33Z",
      "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": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1390.83708850739,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.07494801160975,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 65,
      "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": 33,
      "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": "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": 41,
      "max_score": null,
      "measured_at": "2026-08-04T23:17:48Z",
      "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": 65,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.1077884272852,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.07194976252669,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.79574548966636,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "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": 36,
      "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-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": 36,
      "max_score": null,
      "measured_at": "2026-08-03T12:29:03Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1387.7364854445989,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.92088394835182,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "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": 68,
      "draws": 6,
      "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": 59,
      "max_score": null,
      "measured_at": "2026-09-10T01:42:25Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1376.3097819269658,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.919571760376535,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 88,
      "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": 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": "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": 56,
      "max_score": null,
      "measured_at": "2026-08-03T13:20:46Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1375.9572202695874,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.24873264001045,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "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": 30,
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T01:58:27Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1382.3956787117227,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.06289260104517,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 94,
      "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": 45,
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:57:10Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1369.4305277949966,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 38.84474260375074,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 44,
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:46:15Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1363.2498048504203,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 38.29161379644027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "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": 36,
      "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": 40,
      "max_score": null,
      "measured_at": "2026-08-05T03:20:33Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1355.6151985484798,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.40890126819568,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 214,
      "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": 77,
      "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": "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": 107,
      "max_score": null,
      "measured_at": "2026-09-10T04:44:07Z",
      "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": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1333.976725690619,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.148171051976554,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 76,
      "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": 36,
      "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": "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": 41,
      "max_score": null,
      "measured_at": "2026-08-05T00:42:50Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1351.780972077647,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.109053054838675,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 33
    },
    {
      "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": 1,
      "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": 55,
      "max_score": null,
      "measured_at": "2026-08-05T02:42:09Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1356.0188073823756,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 36.17363038802949,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 33.47940711208657,
      "unilateral_faults": null,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 46,
      "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": "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": 51,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:50Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1318.239164434667,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.87468051476392,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "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": 81,
      "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-5.6-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": 121,
      "max_score": null,
      "measured_at": "2026-09-10T04:44:38Z",
      "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": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1302.406805806133,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.76336759556245,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 74,
      "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": 35,
      "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": 45,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:50Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1317.7760054622622,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.4025425756531,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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": "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": 58,
      "max_score": null,
      "measured_at": "2026-09-10T09:57:11Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1302.5601801283046,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.9571180345745,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "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": 27,
      "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": 38,
      "max_score": null,
      "measured_at": "2026-08-05T00:52:58Z",
      "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": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1311.979408855983,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.417976363713066,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 65,
      "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": 31,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-08-05T02:35:51Z",
      "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": 65,
      "rating_method": "sequential_elo",
      "raw_elo": 1290.844080299784,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.05797596367991,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.79574548966636,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "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": 30,
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T00:54:22Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1283.4075921095573,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.321722084104252,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "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": 43,
      "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": "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": 60,
      "max_score": null,
      "measured_at": "2026-08-04T23:37:39Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1271.9140813081422,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.07434547943685,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 25
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 562,
      "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": 188,
      "draws": 39,
      "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": 353,
      "max_score": null,
      "measured_at": "2026-09-10T10:01:16Z",
      "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": 562,
      "rating_method": "sequential_elo",
      "raw_elo": 1248.2559899500977,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.7144277981412,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 118,
      "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": 59,
      "draws": 7,
      "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": 59,
      "max_score": null,
      "measured_at": "2026-09-10T10:00:19Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1250.09057059966,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.853834414688254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 118,
      "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": 59,
      "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": 77,
      "max_score": null,
      "measured_at": "2026-07-31T20:22:51Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1263.6703813634592,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.744552879877197,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.806447728429966,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "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": 35,
      "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-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": 52,
      "max_score": null,
      "measured_at": "2026-08-05T03:19:33Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1248.3796837667817,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.97553839834991,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 20
    },
    {
      "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": 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": "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": 208,
      "max_score": null,
      "measured_at": "2026-09-10T10:02:24Z",
      "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": 292,
      "rating_method": "sequential_elo",
      "raw_elo": 1243.933403264033,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.963264231692612,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 81
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 550,
      "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": 178,
      "draws": 61,
      "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": 356,
      "max_score": null,
      "measured_at": "2026-09-10T10:09:09Z",
      "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": 550,
      "rating_method": "sequential_elo",
      "raw_elo": 1217.4900636368764,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.288928420260433,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 88,
      "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": 42,
      "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": "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": 47,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:28Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1229.8219327403026,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.820507101588568,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "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": 75,
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-09-10T09:59:37Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1202.5637405728094,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.84086876363679,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 118,
      "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": 59,
      "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": 70,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:25Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1207.1538729649988,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.49605360253772,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "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": 40,
      "draws": 9,
      "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": 59,
      "max_score": null,
      "measured_at": "2026-08-05T05:35:20Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1211.2987002752848,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.254176503754234,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "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": 32,
      "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": "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": 48,
      "max_score": null,
      "measured_at": "2026-08-05T03:20:18Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1212.3309448675193,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.946851868730132,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "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": 77,
      "draws": 11,
      "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": 129,
      "max_score": null,
      "measured_at": "2026-09-10T09:58:34Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1187.329180941812,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.64947969953627,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 310,
      "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": 147,
      "draws": 20,
      "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": 192,
      "max_score": null,
      "measured_at": "2026-09-10T10:25:37Z",
      "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": 310,
      "rating_method": "sequential_elo",
      "raw_elo": 1149.9302789153699,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.36329166385045,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 118,
      "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": 59,
      "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": 77,
      "max_score": null,
      "measured_at": "2026-09-10T10:05:38Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1144.2341444565989,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 21.57553878118651,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 272,
      "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": 89,
      "draws": 40,
      "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": 193,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:47Z",
      "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": 272,
      "rating_method": "sequential_elo",
      "raw_elo": 1129.6690678120026,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 21.41082453515432,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 139,
      "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": 62,
      "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": "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": 100,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:23Z",
      "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": 139,
      "rating_method": "sequential_elo",
      "raw_elo": 1135.9434964465404,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 21.15098392596629,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 118,
      "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": 59,
      "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": 81,
      "max_score": null,
      "measured_at": "2026-09-10T10:05:07Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1135.9605316579625,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.92851700650774,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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": 82,
      "max_score": null,
      "measured_at": "2026-09-10T10:05:29Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1134.8331246095388,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.84035033409872,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "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": 76,
      "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-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": 148,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:09Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1125.533713227516,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.816885503902856,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 137,
      "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": 63,
      "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": 95,
      "max_score": null,
      "measured_at": "2026-09-10T10:02:48Z",
      "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": 137,
      "rating_method": "sequential_elo",
      "raw_elo": 1129.6109725111855,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.636672560776855,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 118,
      "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": 59,
      "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": 80,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:04Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1130.7908652219028,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.524233311661888,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 284,
      "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": 96,
      "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": "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": 201,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:23Z",
      "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": 284,
      "rating_method": "sequential_elo",
      "raw_elo": 1112.70739237112,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.124655747942903,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 118,
      "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": 59,
      "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": 80,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:24Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1123.5806586176955,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 19.960373147257805,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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": 74,
      "max_score": null,
      "measured_at": "2026-09-10T10:05:55Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1108.0482505341167,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 18.745691425032618,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 204,
      "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": 78,
      "draws": 4,
      "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": 152,
      "max_score": null,
      "measured_at": "2026-08-03T14:04:05Z",
      "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": 204,
      "rating_method": "sequential_elo",
      "raw_elo": 1103.9436983097544,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 18.209581535374213,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.523431578963063,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 3,
      "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": 89,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:09Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1097.337741745947,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.908096945753098,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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": "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": 82,
      "max_score": null,
      "measured_at": "2026-09-10T10:15:29Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1092.640375258977,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.540748548543018,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 532,
      "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": 180,
      "draws": 7,
      "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": 428,
      "max_score": null,
      "measured_at": "2026-09-10T10:09:06Z",
      "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": 532,
      "rating_method": "sequential_elo",
      "raw_elo": 1063.2432752679865,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 16.1949707891289,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 134,
      "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": 60,
      "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": "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": 93,
      "max_score": null,
      "measured_at": "2026-09-10T10:05:24Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1071.4948750931987,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 16.062391875633203,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 118,
      "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": 59,
      "draws": 2,
      "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": 93,
      "max_score": null,
      "measured_at": "2026-09-10T10:09:01Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1015.9346068947455,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 11.54212333087466,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-09-10T10:09:47Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1004.422711902854,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.641858004366158,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "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": 9,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:47Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 2100.234118121552,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": null,
      "wins": 115
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 10,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:12Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 2085.516679771956,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 98.77394998739801,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 114
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 2,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:40Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 2085.499777586485,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 98.77254193497626,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 122
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 7,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:32Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 2071.65343311513,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 97.61905921533831,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 117
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 6,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:17Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 2051.5484644930266,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 95.94419593771026,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 118
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "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": 85,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:35Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 2038.1479062581575,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 95.50333681723484,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 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": 18,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:28Z",
      "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": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 2014.2567973068285,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 92.8375786081501,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": null,
      "wins": 230
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "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": 24,
      "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": 1,
      "max_score": null,
      "measured_at": "2026-08-05T04:12:54Z",
      "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": 52,
      "rating_method": "sequential_elo",
      "raw_elo": 1939.9466836858041,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 85.05036844756516,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.930281974344517,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "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": 25,
      "max_score": null,
      "measured_at": "2026-09-10T10:38:58Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1888.7253917920593,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 82.38006707268947,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": null,
      "wins": 99
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "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": 32,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-08-05T04:35:52Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1897.9650985373178,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 82.05925729033785,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 210,
      "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": 86,
      "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": 48,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:12Z",
      "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": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1843.711746417953,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 79.3166000382083,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 132,
      "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": 66,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-05T04:43:15Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1839.0854245052378,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 77.13223675647313,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.664741204687253,
      "unilateral_faults": 0,
      "wins": 108
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "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": 86,
      "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": 72,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:19Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1796.0495447757285,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 75.33510562810226,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "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": 62,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:17Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1799.8280691620685,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 74.97439218948013,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 39,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:15Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1797.9218119745026,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 74.8155896456324,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 85
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 140,
      "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": 65,
      "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": 46,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:09Z",
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1781.9845675213576,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 73.66211615758745,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 66,
      "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": 33,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-03T14:13:52Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1788.427811410473,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 72.9341507961126,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:25Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1771.7419329089944,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 72.63465025280209,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 51,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:14Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1770.5152776722223,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 72.53246258720579,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:09Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1764.710116676486,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 72.04885820287524,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 56,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:19Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1762.832763073679,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 71.89246349927906,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "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": 29,
      "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": 10,
      "max_score": null,
      "measured_at": "2026-08-05T02:27:25Z",
      "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": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1775.8567877936537,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 71.61968219996771,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:24Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1756.8345831771405,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 71.39277949428767,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 51,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:18Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1735.5902511796148,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 69.62300048148802,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 57,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:15Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1730.9511982705933,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 69.23653982560063,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "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": 35,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-08-05T01:31:22Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1738.437095863048,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 68.88596501989264,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "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": 30,
      "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": 14,
      "max_score": null,
      "measured_at": "2026-08-05T03:23:19Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1736.7603940051758,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 68.43443121361176,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:21Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1708.102176119845,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 67.33308059374065,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "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": 32,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-08-05T03:27:48Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1708.9421639300028,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 66.31252434317867,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 530,
      "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": 197,
      "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": 216,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:24Z",
      "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": 530,
      "rating_method": "sequential_elo",
      "raw_elo": 1679.6379373271573,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 65.89914757897805,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "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": 62,
      "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": 70,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:21Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1688.6451933819492,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 65.71219838826845,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 55,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:35Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1686.0872386532578,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 65.49910556920233,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 61,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:41Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1684.0539106103315,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 65.32971726850512,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 137,
      "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": 67,
      "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": 63,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:45Z",
      "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": 137,
      "rating_method": "sequential_elo",
      "raw_elo": 1680.3198610156614,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 65.16250365749241,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "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": 36,
      "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": 25,
      "max_score": null,
      "measured_at": "2026-08-05T04:28:28Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1690.0437032215139,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 64.90905738242017,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "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": 38,
      "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": 25,
      "max_score": null,
      "measured_at": "2026-08-05T05:17:46Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1685.7742661744414,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 64.65603985716929,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "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": 85,
      "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": 85,
      "max_score": null,
      "measured_at": "2026-09-10T10:25:59Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1657.1377622614993,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 63.76292923051514,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "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": 62,
      "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": 54,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:26Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1659.5943657506098,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 63.292091931054706,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 67,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:36Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1656.7525702876383,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 63.05535349326236,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:43Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1653.943529613308,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 62.82134372387497,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 64,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:40Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1651.1504455479346,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 62.58866323477045,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 210,
      "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": 87,
      "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": 71,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:37Z",
      "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": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1629.7367324775714,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 61.491210707100855,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "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": 62,
      "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": 60,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:41Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1636.2057518933793,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 61.34368150573174,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 65,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:37Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1633.9085154706795,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 61.15230806980508,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "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": 32,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-08-03T10:15:02Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1643.2683262324292,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 60.77934776395481,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "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": 85,
      "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": 99,
      "max_score": null,
      "measured_at": "2026-09-10T10:25:59Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1620.0527433433303,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 60.67352692884251,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 86,
      "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": 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": "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": 32,
      "max_score": null,
      "measured_at": "2026-08-05T02:27:33Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1628.2563386094778,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 60.08935840000744,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 270,
      "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": 101,
      "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": 104,
      "max_score": null,
      "measured_at": "2026-09-10T03:12:25Z",
      "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": 270,
      "rating_method": "sequential_elo",
      "raw_elo": 1607.2119914999753,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 59.88458279946914,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 58,
      "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": 29,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-08-03T08:56:19Z",
      "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": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1630.9732967737627,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 59.55002702144701,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 36
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 394,
      "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": 197,
      "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": 191,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:35Z",
      "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": 394,
      "rating_method": "sequential_elo",
      "raw_elo": 1612.2752770256213,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 59.42904163978228,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.529728340267163,
      "unilateral_faults": 0,
      "wins": 203
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "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": 64,
      "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": 78,
      "max_score": null,
      "measured_at": "2026-09-10T04:00:11Z",
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1611.935450984356,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 59.36839361358854,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 50
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "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": "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": 44,
      "max_score": null,
      "measured_at": "2026-07-31T02:14:48Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1614.0469058467165,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 57.914631415085466,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.725467857697634,
      "unilateral_faults": null,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "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": 34,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-08-03T15:11:05Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1602.6753490524998,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 57.519301106513744,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "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": 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": "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": 68,
      "max_score": null,
      "measured_at": "2026-09-10T05:24:20Z",
      "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": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1576.4532916630528,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 56.520023604329275,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 356,
      "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": 126,
      "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": 153,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:22Z",
      "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": 356,
      "rating_method": "sequential_elo",
      "raw_elo": 1555.2590306763939,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.81717567058087,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 203
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 168,
      "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": 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": "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": 98,
      "max_score": null,
      "measured_at": "2026-09-10T10:38:58Z",
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.3496621939992,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.77515547852249,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 186,
      "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": 93,
      "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": 100,
      "max_score": null,
      "measured_at": "2026-09-10T07:08:48Z",
      "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": 186,
      "rating_method": "sequential_elo",
      "raw_elo": 1548.4272881975826,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.57488465434671,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 72,
      "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": 34,
      "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": 30,
      "max_score": null,
      "measured_at": "2026-07-30T20:24:39Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.3694192320527,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.43964322154773,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "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": 69,
      "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": 76,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:37Z",
      "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": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1551.253062152687,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.42069483699623,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 298,
      "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": 101,
      "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": 143,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:23Z",
      "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": 298,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.6745398626697,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.18880756070461,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 201,
      "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": 94,
      "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": 102,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:25Z",
      "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": 201,
      "rating_method": "sequential_elo",
      "raw_elo": 1541.4606321797407,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.086740109183,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 74,
      "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": 37,
      "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": 29,
      "max_score": null,
      "measured_at": "2026-08-05T01:45:01Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.40103047392,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.07809949631,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 178,
      "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": 89,
      "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": 87,
      "max_score": null,
      "measured_at": "2026-09-10T08:06:59Z",
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1541.8464737999418,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.97280588441953,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 74,
      "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": 37,
      "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": 30,
      "max_score": null,
      "measured_at": "2026-08-05T02:50:32Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.9374591439505,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.03980999081365,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "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": 27,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-07-31T01:11:18Z",
      "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": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.3867558441927,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 52.848317065935,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 140,
      "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": 70,
      "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": 79,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:24Z",
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.4117810372288,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 52.78791504126206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 274,
      "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": 93,
      "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": 144,
      "max_score": null,
      "measured_at": "2026-09-10T06:10:34Z",
      "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": 274,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.210308630917,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 52.151765643097974,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 136,
      "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": 68,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:19Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1521.2495664877445,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 51.90066980814227,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 68,
      "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": 34,
      "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": 30,
      "max_score": null,
      "measured_at": "2026-07-31T03:28:34Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1528.7719349901129,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 51.362707846858044,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 166,
      "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": 83,
      "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": 86,
      "max_score": null,
      "measured_at": "2026-09-10T07:11:41Z",
      "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": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.681844836616,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 51.1220637969503,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 270,
      "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": 102,
      "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": 123,
      "max_score": null,
      "measured_at": "2026-09-10T04:41:01Z",
      "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": 270,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.6086176884314,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.753970891959106,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 300,
      "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": 100,
      "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": 143,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:32Z",
      "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": 300,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.746440183285,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.61905487171679,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 102,
      "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": 51,
      "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": 55,
      "max_score": null,
      "measured_at": "2026-07-31T03:28:43Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1524.5127418063732,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.39267058934464,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 25.674278837447822,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 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": "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": 40,
      "max_score": null,
      "measured_at": "2026-08-05T05:26:41Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.4961528383703,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.35863516788991,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 130,
      "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": 65,
      "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": 55,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:35Z",
      "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": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.9116984620532,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.3085497072,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 64,
      "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": 32,
      "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": 33,
      "max_score": null,
      "measured_at": "2026-08-03T14:04:15Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1517.0750056649872,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.266694773888176,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 31
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 160,
      "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": 75,
      "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": 87,
      "max_score": null,
      "measured_at": "2026-08-04T01:46:38Z",
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.128045469491,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.106011352032695,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.244710982631887,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "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": 69,
      "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": 73,
      "max_score": null,
      "measured_at": "2026-09-10T01:35:09Z",
      "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": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.6605915888285,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.789511908530514,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 354,
      "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": 121,
      "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": 180,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:29Z",
      "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": 354,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.3897304730226,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.57515742958389,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 557,
      "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": 188,
      "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": 264,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:12Z",
      "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": 553,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.5671295846262,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.274306768900956,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 289
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 176,
      "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": 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": "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": 89,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:43Z",
      "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": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.4006055300267,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.08988614590849,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 378,
      "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": 153,
      "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": 177,
      "max_score": null,
      "measured_at": "2026-09-10T07:08:49Z",
      "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": 378,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.5103578202652,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.90130757412859,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.293412226141589,
      "unilateral_faults": 0,
      "wins": 201
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 47,
      "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": 46,
      "max_score": null,
      "measured_at": "2026-08-05T04:43:24Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.1477983527448,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.60664400355754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "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": 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": "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": 45,
      "max_score": null,
      "measured_at": "2026-08-05T03:34:26Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.1227460326932,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.5556009285104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 53
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 533,
      "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": 176,
      "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": 246,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:44Z",
      "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": 533,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.2476393987372,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.1277645295087,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 261,
      "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": 95,
      "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": 113,
      "max_score": null,
      "measured_at": "2026-09-10T07:11:19Z",
      "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": 261,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.5273767081653,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.046939930059665,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 86,
      "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": 42,
      "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": 39,
      "max_score": null,
      "measured_at": "2026-08-05T05:19:10Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.4064114364373,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.02249928924504,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "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": 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": "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": 41,
      "max_score": null,
      "measured_at": "2026-08-05T00:37:00Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.0240469090763,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.74072823827207,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 150,
      "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": 75,
      "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": 82,
      "max_score": null,
      "measured_at": "2026-09-10T10:25:47Z",
      "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": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.3166092846598,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.20969665141295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 92,
      "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": 44,
      "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": 45,
      "max_score": null,
      "measured_at": "2026-08-03T15:18:37Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.8109077124877,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.42393579584542,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 154,
      "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": 77,
      "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": 74,
      "max_score": null,
      "measured_at": "2026-09-10T08:07:41Z",
      "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": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.4326426470998,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.33821644839612,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 84,
      "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": 42,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-08-05T01:37:35Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.726826181827,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.17467565559709,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "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": 44,
      "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": 43,
      "max_score": null,
      "measured_at": "2026-08-05T04:02:22Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.7629546063713,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.093227838491046,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 140,
      "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": 70,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-09-10T05:27:41Z",
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.9404458311392,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.08417494737303,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 84,
      "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": 40,
      "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": 40,
      "max_score": null,
      "measured_at": "2026-08-04T21:46:04Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.0882405137008,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.954865800457036,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 178,
      "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": 89,
      "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": 91,
      "max_score": null,
      "measured_at": "2026-09-10T05:24:32Z",
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.8985365440951,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.64654917987288,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 76,
      "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": 37,
      "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": 50,
      "max_score": null,
      "measured_at": "2026-08-05T02:09:18Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.5857937905953,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.56327909407335,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 288,
      "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": 96,
      "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": 135,
      "max_score": null,
      "measured_at": "2026-09-10T05:23:43Z",
      "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": 288,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.1416955480029,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.781096360775045,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 4,
      "attempted_matches": 1174,
      "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": 390,
      "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": 631,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:21Z",
      "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": 1174,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.8637837101146,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.43538755960546,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 543
    },
    {
      "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": 342,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:32Z",
      "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": 592,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.556676770801,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.412761651647685,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 250
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 396,
      "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": 198,
      "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": 207,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:29Z",
      "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": 396,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.2360449335408,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.26903335828475,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.6475730333305307,
      "unilateral_faults": 0,
      "wins": 189
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 152,
      "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": 75,
      "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": 83,
      "max_score": null,
      "measured_at": "2026-08-05T04:34:28Z",
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.6299185770467,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.15012153636137,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.244710982631887,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 216,
      "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": 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-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": 110,
      "max_score": null,
      "measured_at": "2026-09-10T04:00:04Z",
      "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": 216,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.974888101097,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.04906884876752,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 128,
      "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": 64,
      "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": 55,
      "max_score": null,
      "measured_at": "2026-09-10T06:10:25Z",
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.4944080709313,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.920382254410434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 69,
      "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": 34,
      "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": 39,
      "max_score": null,
      "measured_at": "2026-08-05T03:50:20Z",
      "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": 69,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.4173564751177,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.61480276704312,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.01143046671968,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "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": 52,
      "max_score": null,
      "measured_at": "2026-08-05T05:19:01Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.9512232436878,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.60735748459359,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.79047988958712,
      "unilateral_faults": null,
      "wins": 50
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 166,
      "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": 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": "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": 81,
      "max_score": null,
      "measured_at": "2026-08-05T05:16:33Z",
      "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": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.0098278142677,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.26122886658135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.807372224754609,
      "unilateral_faults": 0,
      "wins": 85
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 61,
      "max_score": null,
      "measured_at": "2026-09-10T10:25:58Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1403.884604633261,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.98995032235631,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 108,
      "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": 54,
      "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": 61,
      "max_score": null,
      "measured_at": "2026-07-31T03:07:18Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.9613762014483,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.566578731207976,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 212,
      "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": 77,
      "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": 112,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:08Z",
      "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": 212,
      "rating_method": "sequential_elo",
      "raw_elo": 1389.9379293174322,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.52534176853236,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 148,
      "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": 71,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-09-10T07:08:48Z",
      "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": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.6769732770667,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.30685657778837,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "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": 62,
      "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": 53,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:15Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1388.8368134317343,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 40.73637995542009,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "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": 35,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-08-05T04:09:17Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1400.0415201193246,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 40.695604031124134,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 29
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 572,
      "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": 205,
      "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": 356,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:01Z",
      "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": 572,
      "rating_method": "sequential_elo",
      "raw_elo": 1375.6177949642233,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 40.64504874231809,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 154,
      "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": 77,
      "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": 79,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:14Z",
      "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": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1382.2993539809847,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 40.49569702277399,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "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": 62,
      "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": 58,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:14Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1378.0542771114426,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.83813064889331,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 372,
      "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": 186,
      "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": 223,
      "max_score": null,
      "measured_at": "2026-09-10T10:38:57Z",
      "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": 372,
      "rating_method": "sequential_elo",
      "raw_elo": 1377.4600285305544,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.78862621321775,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 149
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "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": 82,
      "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": 132,
      "max_score": null,
      "measured_at": "2026-09-10T07:08:47Z",
      "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": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1366.7542420762652,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.6557227947306,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 206,
      "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": 77,
      "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": 111,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:44Z",
      "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": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1350.9626991135992,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 38.245619988996886,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 140,
      "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": 70,
      "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": 75,
      "max_score": null,
      "measured_at": "2026-09-10T08:07:02Z",
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1350.283417023103,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.698846705657566,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 140,
      "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": 70,
      "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": 57,
      "max_score": null,
      "measured_at": "2026-09-10T01:25:22Z",
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1346.062927829242,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.34725489284307,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 280,
      "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": 96,
      "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": 163,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:32Z",
      "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": 280,
      "rating_method": "sequential_elo",
      "raw_elo": 1319.3894482362023,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.94359963093725,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 84,
      "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": 41,
      "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": 46,
      "max_score": null,
      "measured_at": "2026-08-04T23:37:48Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1335.0085860056213,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.618293744936246,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "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": 41,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-08-03T11:10:49Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1330.5150146991402,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.20066576920315,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "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": 41,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-08-05T02:50:21Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1320.2237612604144,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.386630045412275,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 282,
      "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": 96,
      "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": 180,
      "max_score": null,
      "measured_at": "2026-09-10T10:25:51Z",
      "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": 282,
      "rating_method": "sequential_elo",
      "raw_elo": 1300.0532231004343,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.33981389682823,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "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": 62,
      "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": 61,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:46Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1311.9620137214838,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.33225262601179,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "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": 35,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-08-05T04:12:54Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1318.9452867243672,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.99435555624251,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:14Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1299.509218523322,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.294860836288024,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 150,
      "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": 69,
      "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": 98,
      "max_score": null,
      "measured_at": "2026-08-05T02:50:09Z",
      "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": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1307.793294134663,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.07868627119113,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.570138866854082,
      "unilateral_faults": 4,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 70,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:39Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1296.2785108029113,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.02572369793326,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:37Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1294.2455644828358,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.856367197016354,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 268,
      "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": 88,
      "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": 177,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:18Z",
      "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": 268,
      "rating_method": "sequential_elo",
      "raw_elo": 1279.0698787444887,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.54088523137084,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 136,
      "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": 65,
      "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": 76,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:24Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1281.5719820233626,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.934103720162618,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "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": 62,
      "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": 68,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:44Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1278.4467772054588,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.54023439724443,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 86,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:24Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1277.4160766202162,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.45437091777823,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 266,
      "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": 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": "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": 180,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:21Z",
      "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": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1265.4548452950958,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.399076922756784,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "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": 62,
      "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": 72,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:29Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1269.2768040275703,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.7763211765297,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "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": 38,
      "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": 54,
      "max_score": null,
      "measured_at": "2026-08-05T01:38:57Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1276.8149612185298,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.72713242170736,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "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": 80,
      "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": 132,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:38Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1252.9129029601745,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.08859800058072,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 266,
      "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": 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": "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": 190,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:20Z",
      "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": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1208.9920377589156,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.69538975608495,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 70,
      "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": 34,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-08-03T21:49:16Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1227.6442414952623,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.276982761125968,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 2,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "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": 28,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-07-31T03:28:04Z",
      "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": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1205.2540746232235,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.0096350455345,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "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": 64,
      "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": 101,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:01Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1175.0341089574347,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.05886622894134,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 70,
      "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": 33,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-08-04T23:43:45Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1176.2953930743706,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.05622295359803,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "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": 34,
      "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": 48,
      "max_score": null,
      "measured_at": "2026-08-03T22:56:47Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1168.9821053977837,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 21.390078464798552,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 2,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 87,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:06Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1138.6513341974915,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 19.894443832996753,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 88,
      "max_score": null,
      "measured_at": "2026-09-10T10:38:59Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1127.7345872672606,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 18.985013985665347,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "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": 35,
      "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": 59,
      "max_score": null,
      "measured_at": "2026-08-04T01:46:38Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1132.1434855724015,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 18.37810686686219,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 2,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "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": 33,
      "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": 50,
      "max_score": null,
      "measured_at": "2026-08-04T01:12:37Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1126.7838784610865,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.815282073084678,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 2,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 210,
      "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": 77,
      "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": 168,
      "max_score": null,
      "measured_at": "2026-09-10T10:38:55Z",
      "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": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1092.582795701611,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 16.743097937091278,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 266,
      "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": 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": "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": 225,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:04Z",
      "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": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1075.9620883310313,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 15.613204983285852,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 56,
      "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": 28,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-07-31T03:28:34Z",
      "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": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1094.6976995498242,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 14.799632473606307,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "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": 34,
      "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": 61,
      "max_score": null,
      "measured_at": "2026-08-05T01:39:12Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1076.1156014586118,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 13.765200753063453,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 99,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:02Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1050.380743783233,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.540979465146396,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 105,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:00Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1039.7885406295645,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 11.658586041674393,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 109,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:44Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1027.8258491263755,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.662022800175135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 109,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:22Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 940.4778015280162,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 3.385411727320254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 118,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:47Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 899.8395013993829,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "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": 3,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:12Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 2166.2747750373137,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": null,
      "wins": 119
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 278,
      "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": 101,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:03Z",
      "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": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 2037.1859548088862,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 89.21089685186311,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 258
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 61,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:08Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 2015.5208557563683,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 86.09465836643398,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 102
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08: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": 61,
      "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": "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": 20,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:17Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 2004.6104572049926,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 85.08829766988379,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 101
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 61,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-09-10T10:25:38Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1965.2290624670259,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 81.45581003407503,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 109
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 272,
      "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": 100,
      "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": 33,
      "max_score": null,
      "measured_at": "2026-09-10T10:09:31Z",
      "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": 272,
      "rating_method": "sequential_elo",
      "raw_elo": 1948.7095603306732,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 81.02581011754175,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 122,
      "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": 61,
      "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": 28,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:06Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1912.6127034227568,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 76.60254683856613,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 94
    },
    {
      "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": 24,
      "max_score": null,
      "measured_at": "2026-09-10T10:09:21Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1902.679336383488,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 75.68630623327066,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": null,
      "wins": 97
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:x-ai-grok-4-5:a7aa1873ad17dbcc",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "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-4.5",
        "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": 10,
      "max_score": null,
      "measured_at": "2026-08-04T23:52:07Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1906.4614489539558,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 75.36004018487888,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 61,
      "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": 26,
      "max_score": null,
      "measured_at": "2026-09-10T10:08:58Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1893.5285342223358,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 74.84224837474918,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 206,
      "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": 83,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-09-10T10:05:15Z",
      "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": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1879.7469609720076,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 74.33339438299416,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 122,
      "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": 61,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-09-10T10:15:28Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1885.1060573978139,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 74.06537027960984,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 106
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 156,
      "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": 78,
      "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": 19,
      "max_score": null,
      "measured_at": "2026-08-05T05:26:16Z",
      "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": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1877.7575378139375,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 72.56224223151698,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.51792189268726,
      "unilateral_faults": 0,
      "wins": 137
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 206,
      "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": 84,
      "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": 60,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:40Z",
      "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": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1840.334484911061,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 70.6980398471637,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 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": 23,
      "max_score": null,
      "measured_at": "2026-09-10T10:08:54Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1843.3344616499016,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 70.21241367175236,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": null,
      "wins": 99
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 61,
      "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": 31,
      "max_score": null,
      "measured_at": "2026-09-10T10:15:30Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1842.870478313909,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 70.16961646402447,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 276,
      "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": 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": "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": 68,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:35Z",
      "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": 276,
      "rating_method": "sequential_elo",
      "raw_elo": 1825.4782335252758,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 69.67529740665044,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 122,
      "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": 61,
      "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": 28,
      "max_score": null,
      "measured_at": "2026-09-10T10:15:31Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1824.43663835412,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 68.46930350710791,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 94
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 206,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-sol:e7389fafab42de55",
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "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-5.6-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": 49,
      "max_score": null,
      "measured_at": "2026-09-10T10:05:49Z",
      "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": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1802.802960584029,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 67.23618180536194,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 122,
      "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": 61,
      "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": 36,
      "max_score": null,
      "measured_at": "2026-09-10T10:09:00Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1803.034470342118,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 66.49519590628826,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-5:a77a9da79f1450e0",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "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-5.5",
        "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": 16,
      "max_score": null,
      "measured_at": "2026-08-05T03:02:23Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1795.716933688497,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 64.88666662466245,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:f9ec308f9bb8850b",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": "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": 36,
      "max_score": null,
      "measured_at": "2026-09-10T10:05:31Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1782.8322402319461,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 64.6317689865653,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 61,
      "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": 38,
      "max_score": null,
      "measured_at": "2026-09-10T10:05:58Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1767.790823738796,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 63.24436867228078,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 61,
      "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": 33,
      "max_score": null,
      "measured_at": "2026-09-10T10:05:51Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1758.5557003334645,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 62.39253313399566,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 61,
      "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": 43,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:03Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1757.519707353812,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 62.29697451515008,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 126,
      "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": 55,
      "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": 30,
      "max_score": null,
      "measured_at": "2026-08-05T04:44:12Z",
      "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": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1769.8149510159715,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 62.145467936039324,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.755723064737715,
      "unilateral_faults": 0,
      "wins": 96
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:thinkingmachines-inkling:a1a9848a1d14b67e",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "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": "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": 27,
      "max_score": null,
      "measured_at": "2026-08-05T03:33:08Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1745.1879860541585,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 60.57535339573391,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08: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": 32,
      "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": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T04:47:27Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1751.2546865112345,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 60.46952997771049,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:meta-muse-spark-1-3:111be2eb4c7d6522",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 8,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-09-10T10:02:54Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1729.0069973801026,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 59.66699995147499,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 276,
      "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": 109,
      "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": 67,
      "max_score": null,
      "measured_at": "2026-09-09T11:45:10Z",
      "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": 276,
      "rating_method": "sequential_elo",
      "raw_elo": 1710.8842433394993,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 59.105299689263475,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-6-flash:13a24e3021af753a",
      "capped_draws": 47,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 96,
      "draws": 47,
      "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": 89,
      "max_score": null,
      "measured_at": "2026-09-10T11:10:23Z",
      "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": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1707.404877029335,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 58.67238008178089,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 70,
      "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": 33,
      "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": 19,
      "max_score": null,
      "measured_at": "2026-08-05T02:16:17Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1722.852641589118,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 58.04739613214064,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 51
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 356,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-5:2bf46853c4c2a3bc",
      "capped_draws": 39,
      "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": "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": 88,
      "max_score": null,
      "measured_at": "2026-09-10T10:00:20Z",
      "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": 356,
      "rating_method": "sequential_elo",
      "raw_elo": 1700.9563586930085,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 57.326164470494916,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.624947000159003,
      "unilateral_faults": 0,
      "wins": 229
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 368,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:stealth-ox-alpha:fe3b437dca2c4367",
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 184,
      "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": "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": 149,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:17Z",
      "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": 368,
      "rating_method": "sequential_elo",
      "raw_elo": 1691.5039555971996,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 56.216676213796916,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.2127743389130075,
      "unilateral_faults": 0,
      "wins": 170
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:moonshotai-kimi-k2-7-code:0eac35852db14de0",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 6,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-08-03T11:19:09Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1668.9996561249077,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.14046672619939,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-8-max:644816d2bc8a5f5c",
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "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": "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": 54,
      "max_score": null,
      "measured_at": "2026-09-10T09:55:40Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1632.9127357518287,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.977952428863446,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": null,
      "draws": 18,
      "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": 40,
      "max_score": null,
      "measured_at": "2026-07-31T03:36:31Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1652.7180520158581,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.95958014662912,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.973505697509715,
      "unilateral_faults": null,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:meta-muse-spark-1-2:0ef600658249027b",
      "capped_draws": 42,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 86,
      "draws": 42,
      "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": 77,
      "max_score": null,
      "measured_at": "2026-09-09T23:36:16Z",
      "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": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1623.6330641273657,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.80349713326343,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-4-5:959db58a0f4d59b9",
      "capped_draws": 3,
      "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": "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": 18,
      "max_score": null,
      "measured_at": "2026-08-03T01:17:19Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1644.8221338731084,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.580259976688616,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-sol:92a27bf667504f91",
      "capped_draws": 47,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 47,
      "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": 75,
      "max_score": null,
      "measured_at": "2026-09-10T11:07:22Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1614.9647465144133,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.92253340064839,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-5:1a25631bf54a6363",
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 35,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-08-02T22:46:40Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1619.4173554954286,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.92973960121274,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4:483e8409583d40a0",
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 83,
      "draws": 27,
      "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": 85,
      "max_score": null,
      "measured_at": "2026-09-10T11:09:05Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1604.0284164228153,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.913780813210096,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:meta-muse-spark-1-2:539f99e7c4c4b6ea",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 89,
      "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": "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": 124,
      "max_score": null,
      "measured_at": "2026-09-10T07:15:22Z",
      "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": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1600.6634489201153,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.684810281393695,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-8-flash:83795e08736dcbd6",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-09-10T11:11:52Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1585.921427724455,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.49569805612314,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:z-ai-glm-5-3:2dbca3140c06e14c",
      "capped_draws": 33,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": "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": 50,
      "max_score": null,
      "measured_at": "2026-09-10T09:55:39Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1572.2266605384239,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.20578955238555,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 142,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4-nano:4caf0453cfb54e62",
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 69,
      "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": "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": 45,
      "max_score": null,
      "measured_at": "2026-08-04T20:41:31Z",
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1568.270065288822,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.81658368870027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.213976730923585,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:z-ai-glm-5-2:5ea14bc9644b6a2b",
      "capped_draws": 44,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 53,
      "draws": 44,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-07-31T20:23:06Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1575.4309777408212,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.775234894409756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.725467857697634,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 434,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:stealth-ox-alpha:6719f8157bcde29f",
      "capped_draws": 132,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 217,
      "draws": 132,
      "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": 192,
      "max_score": null,
      "measured_at": "2026-09-10T09:59:50Z",
      "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": 434,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.3224253686287,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 40.48839717718149,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.44449391112387104,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 802,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:o3:1084c60ee563e860",
      "capped_draws": 393,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 286,
      "draws": 393,
      "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": 205,
      "max_score": null,
      "measured_at": "2026-09-10T11:10:18Z",
      "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": 802,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.9587134875176,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.423745439118036,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 128,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-8-flash:e50b23a03b02a00c",
      "capped_draws": 41,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "draws": 41,
      "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": 55,
      "max_score": null,
      "measured_at": "2026-09-09T22:53:54Z",
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.9177376052087,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.35230726139709,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-flash:14b865d3f352c468",
      "capped_draws": 43,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": "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": 61,
      "max_score": null,
      "measured_at": "2026-09-10T11:08:34Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.8384399978336,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.01671077415587,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 542,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-6-flash:b4583ef7c04d45cd",
      "capped_draws": 212,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 195,
      "draws": 212,
      "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": 150,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:05Z",
      "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": 542,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.5632904173685,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 38.850120833000595,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-5:3449c1aec50b70b2",
      "capped_draws": 38,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "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-v2.5",
        "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": 21,
      "max_score": null,
      "measured_at": "2026-08-04T21:46:23Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.7533109604456,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 38.526779758866994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-5-flash:188028ef432c73f8",
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "draws": 49,
      "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": 58,
      "max_score": null,
      "measured_at": "2026-09-09T22:54:43Z",
      "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": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.919514273735,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.75365188750678,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 142,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-fable-5:9411c67711dccbe8",
      "capped_draws": 59,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 71,
      "draws": 59,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-09-10T04:17:05Z",
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.147621438758,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.59961008402652,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 138,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:bytedance-seed-seed-2-0-code:c69120230888411c",
      "capped_draws": 63,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "draws": 63,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-09-09T23:36:18Z",
      "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": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.6155341744773,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.414213664906036,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:minimax-minimax-m3:6639861dd7b73e51",
      "capped_draws": 3,
      "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": "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": 39,
      "max_score": null,
      "measured_at": "2026-08-02T23:32:13Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.3473690224341,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.98498009514775,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 152,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:x-ai-grok-4-6:d94ddefd8b9f53eb",
      "capped_draws": 56,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 76,
      "draws": 56,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-09-10T03:31:28Z",
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.9229355470898,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.65216676371213,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-sonnet-5:a86621e2793b5dec",
      "capped_draws": 95,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 94,
      "draws": 95,
      "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": 94,
      "max_score": null,
      "measured_at": "2026-09-10T10:05:51Z",
      "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": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.9730792715607,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.35038166239203,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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:GB2-08:publication-row.v1:mixed:tencent-hy3-preview:173ea133649c5bcd",
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "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": "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": 33,
      "max_score": null,
      "measured_at": "2026-08-03T12:45:25Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.3689594436266,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.22230343851298,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:o3:f70fd8105d3dfec2",
      "capped_draws": 52,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 52,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-03T12:36:48Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.6927837582004,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.12700070176546,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 194,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-8-max:a791831295f0ee80",
      "capped_draws": 89,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 90,
      "draws": 89,
      "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": 63,
      "max_score": null,
      "measured_at": "2026-09-10T04:18:48Z",
      "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": 194,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.3600386399553,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.11078030295988,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 138,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4-nano:8753e840d1cee063",
      "capped_draws": 69,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 68,
      "draws": 69,
      "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": 38,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:31Z",
      "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": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.7535435217649,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.88890946117016,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.804373924048683,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-terra:4506b3e0a8fb5629",
      "capped_draws": 77,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "draws": 77,
      "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": 58,
      "max_score": null,
      "measured_at": "2026-09-10T06:36:57Z",
      "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": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.233951031026,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.98624406261454,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 192,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-terra:bd3aacb7be18fc49",
      "capped_draws": 72,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 96,
      "draws": 72,
      "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": 85,
      "max_score": null,
      "measured_at": "2026-09-10T06:45:56Z",
      "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": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.7667844873795,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.920915263210404,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-1-flash-lite:4c9cdde1729642af",
      "capped_draws": 34,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 34,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-08-05T05:18:42Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.346762921776,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.74193137879505,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 148,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-terra:ac05ef4b9a51340d",
      "capped_draws": 38,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 74,
      "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-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": 89,
      "max_score": null,
      "measured_at": "2026-09-10T07:13:19Z",
      "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": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.9863882384893,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.57437059459893,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:a3e60c7aa64704be",
      "capped_draws": 52,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 52,
      "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": 19,
      "max_score": null,
      "measured_at": "2026-08-05T01:39:02Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.6513922439997,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.57343311593441,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1,
      "attempted_matches": 170,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-8-27b:739c4d774075dc83",
      "capped_draws": 60,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 85,
      "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": "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": 76,
      "max_score": null,
      "measured_at": "2026-09-10T05:35:56Z",
      "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": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.3847926961248,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.79762104206238,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4-mini:e296afd987da0af3",
      "capped_draws": 30,
      "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": "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": 32,
      "max_score": null,
      "measured_at": "2026-08-05T05:18:57Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.99548468218,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.679683632220694,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-7-max:fa240f0afd3eda59",
      "capped_draws": 59,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 59,
      "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": 26,
      "max_score": null,
      "measured_at": "2026-08-05T01:39:17Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.143126017843,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.549311188071584,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:be72f75fe8d3007b",
      "capped_draws": 60,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "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": "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": 3,
      "max_score": null,
      "measured_at": "2026-07-31T02:32:37Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.3367882425214,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.42192058328905,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemma-4-31b-it:e2b2f6f0f78a1f3f",
      "capped_draws": 66,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "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": "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": 19,
      "max_score": null,
      "measured_at": "2026-08-04T22:07:22Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.1732099119702,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.33433076646184,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 174,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-8-flash:98dfb2fac355b676",
      "capped_draws": 89,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 87,
      "draws": 89,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-09-10T11:08:42Z",
      "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": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.7391422180938,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.30930546094415,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 265,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4:672219b99ff5a80c",
      "capped_draws": 173,
      "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": "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": 42,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:20Z",
      "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": 265,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.8641566204983,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.294233538337693,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-5:53d4c02c8a9496db",
      "capped_draws": 62,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 62,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-08-05T01:22:27Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.2522873931011,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.245278775905984,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:tencent-hy3-preview:7ef07d2849ca4d92",
      "capped_draws": 67,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 67,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-08-05T03:32:28Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.684392050828,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.240220004237862,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:x-ai-grok-build-0-1:55f4f20890a40d69",
      "capped_draws": 67,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 67,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-08-04T23:07:13Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.5973144153943,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.19024732920317,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:minimax-minimax-m3:6f48906184a5bdb8",
      "capped_draws": 71,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 71,
      "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": 14,
      "max_score": null,
      "measured_at": "2026-08-05T01:31:56Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.3080306183583,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.97060306197978,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-7-plus:e4e482b5c34e690f",
      "capped_draws": 74,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 74,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-05T00:36:50Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.1673033832565,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.639092386388416,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 168,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:d3192451477fbf98",
      "capped_draws": 63,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 63,
      "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": 73,
      "max_score": null,
      "measured_at": "2026-09-10T07:15:16Z",
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.3061764466815,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.205666155415027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:nex-agi-nex-n2-pro:b04b6e7c11ec4633",
      "capped_draws": 72,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 72,
      "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": 10,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:06Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.2008821131521,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.091127162093525,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-flash:dac448fbfe2a5737",
      "capped_draws": 99,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 57,
      "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": "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": 11,
      "max_score": null,
      "measured_at": "2026-07-31T03:35:06Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.159833286441,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.029901512891286,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.910536671832062,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-4-8:8ccf8977401d94db",
      "capped_draws": 63,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 63,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-04T23:29:48Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.7365888718184,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.00399105678296,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:z-ai-glm-5-2:f14efcbac580ffaa",
      "capped_draws": 41,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 26,
      "draws": 41,
      "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": 10,
      "max_score": null,
      "measured_at": "2026-07-31T03:34:47Z",
      "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": 52,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.0432306204652,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.888555069388655,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.930281974344517,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 138,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:94c7956182cf2d89",
      "capped_draws": 96,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 67,
      "draws": 96,
      "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": 33,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:22Z",
      "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": 1417.834665740927,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.865118502018596,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.237183532345085,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-4-1:731bd482a4919a05",
      "capped_draws": 64,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "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-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": 15,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:31Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.5680581389895,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.845909406584692,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4-mini:9285646640165917",
      "capped_draws": 50,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 50,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-08-04T06:58:48Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.8326222252044,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.27409368559002,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 2,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-5:024b37c390436d5a",
      "capped_draws": 53,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 53,
      "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": 3,
      "max_score": null,
      "measured_at": "2026-07-31T02:38:23Z",
      "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": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.3599497088626,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.167744907216587,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 142,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:x-ai-grok-4-6:aedb1b245d3cd53f",
      "capped_draws": 102,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 71,
      "draws": 102,
      "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": 31,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:41Z",
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1393.8371725931713,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.992778000535424,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5:16f7def69ce10ccd",
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 49,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-04T23:45:21Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1401.429423608086,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.776555776498935,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:cohere-north-mini-code:4a23759df70ab26b",
      "capped_draws": 72,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 72,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-08-05T03:33:08Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.0183446522383,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.71763057558737,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 147,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:thinkingmachines-inkling-small:6603774c29b8a046",
      "capped_draws": 111,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 68,
      "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": "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": 26,
      "max_score": null,
      "measured_at": "2026-09-10T07:15:50Z",
      "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": 147,
      "rating_method": "sequential_elo",
      "raw_elo": 1390.0220829331531,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.69344443534794,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-1-flash-lite:78a7cfd3a790e8a8",
      "capped_draws": 54,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 54,
      "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": 18,
      "max_score": null,
      "measured_at": "2026-08-05T02:15:42Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.3465620036277,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.658397977334666,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 149,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:thinkingmachines-inkling-small:c4a079d6b58a2c73",
      "capped_draws": 119,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "draws": 119,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-09-10T07:35:02Z",
      "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": 149,
      "rating_method": "sequential_elo",
      "raw_elo": 1388.9166480313115,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.611767026883896,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-5:235a446f3a9f9cd3",
      "capped_draws": 52,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 52,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-07-31T03:34:40Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.6146377235505,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.588150153161838,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:stepfun-step-3-7-flash:0e0f63cf65826515",
      "capped_draws": 46,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "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": "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": 14,
      "max_score": null,
      "measured_at": "2026-08-05T00:38:29Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.3882975295737,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.327373127581367,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-8-max:7b21229bd01e0b5e",
      "capped_draws": 97,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 97,
      "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": 21,
      "max_score": null,
      "measured_at": "2026-09-10T07:29:55Z",
      "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": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1385.047314059996,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.137934382472274,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 134,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-pro:c11fecb63644464d",
      "capped_draws": 119,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 119,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-09-10T05:37:11Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1385.5002735328487,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.13369122148454,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 330,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:moonshotai-kimi-k3:6a00f2f5a49a8584",
      "capped_draws": 246,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 120,
      "draws": 246,
      "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": 67,
      "max_score": null,
      "measured_at": "2026-09-10T10:00:52Z",
      "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": 330,
      "rating_method": "sequential_elo",
      "raw_elo": 1372.3124171079544,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.06475884466223,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 174,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-8-flash:6b8b02f1f727feff",
      "capped_draws": 118,
      "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": "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": 42,
      "max_score": null,
      "measured_at": "2026-09-10T07:24:04Z",
      "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": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1380.4579125856314,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.05501161815919,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 180,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:meituan-longcat-2-0:45102822fc5f9296",
      "capped_draws": 154,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 84,
      "draws": 154,
      "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": 21,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:06Z",
      "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": 180,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.4561955324614,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.9901170337506,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.673739368419632,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:z-ai-glm-5-2:184634950256ca6a",
      "capped_draws": 98,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 98,
      "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": 18,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:45Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1383.290246385837,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.80526655314139,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 186,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:poolside-laguna-s-2-1:533b6103a5973424",
      "capped_draws": 151,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 87,
      "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": "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": 29,
      "max_score": null,
      "measured_at": "2026-08-05T05:33:39Z",
      "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": 186,
      "rating_method": "sequential_elo",
      "raw_elo": 1388.7043408168872,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.79904792639838,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.823251170389485,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 146,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-pro:42034002bcfc5f74",
      "capped_draws": 112,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "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": "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": 26,
      "max_score": null,
      "measured_at": "2026-09-10T11:09:46Z",
      "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": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1379.9427905062857,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.753445741329188,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 152,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:tencent-hy4-preview:2077a0aa15ce66b2",
      "capped_draws": 132,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 76,
      "draws": 132,
      "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": 10,
      "max_score": null,
      "measured_at": "2026-09-10T05:33:12Z",
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1378.5701242686011,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.68709794444988,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:4b9c2bdb10b14302",
      "capped_draws": 54,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 54,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-04T08:41:53Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.7465030285916,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.56700348772194,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:78fb6a9e00356b09",
      "capped_draws": 116,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "draws": 116,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-09-10T07:24:13Z",
      "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": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1377.2103402805674,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.541984464943933,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 138,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:tencent-hy4-preview:b8e7119f660161ad",
      "capped_draws": 117,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "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": "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": 9,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:01Z",
      "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": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1375.432587894814,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.25108478892449,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-8-flash:e1a2822fb5bba20e",
      "capped_draws": 120,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 120,
      "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": 7,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:45Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1373.0820244530325,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.964461868477382,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 136,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:meta-muse-spark-1-3:22ddc49b675eb171",
      "capped_draws": 118,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 68,
      "draws": 118,
      "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": 6,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:51Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1371.8084535422936,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.894039629592516,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:inclusionai-ling-3-0-flash:1ed2a890413ad375",
      "capped_draws": 206,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 91,
      "draws": 206,
      "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": 35,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:59Z",
      "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": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1371.8937477883032,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.740061200441602,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.1611854626755758,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-sonnet-5:73f1b29a5c45562d",
      "capped_draws": 157,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "draws": 157,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-09-10T11:08:22Z",
      "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": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1362.738639703256,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.738941337874866,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-flash:e0a2978fff9e81b1",
      "capped_draws": 104,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": "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": 11,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:57Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1370.3683072257907,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.61336401789957,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-7-max:a92ef5f3c3f212e3",
      "capped_draws": 56,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "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": "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": 29,
      "max_score": null,
      "measured_at": "2026-08-05T05:33:39Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1377.4330339898045,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.609426626585595,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 638,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-6-flash:b574aaabaed70f28",
      "capped_draws": 437,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 223,
      "draws": 437,
      "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": 159,
      "max_score": null,
      "measured_at": "2026-09-10T04:50:58Z",
      "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": 638,
      "rating_method": "sequential_elo",
      "raw_elo": 1356.0600605839268,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.519487645498753,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 142,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:openai-gpt-oss-120b:59563b7e90e4a253",
      "capped_draws": 113,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 71,
      "draws": 113,
      "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": 19,
      "max_score": null,
      "measured_at": "2026-09-10T06:42:39Z",
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1366.298434717585,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.452641331825593,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 560,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:poolside-laguna-s-2-1:07eac22bdea1b9b3",
      "capped_draws": 420,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 202,
      "draws": 420,
      "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": 112,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:54Z",
      "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": 560,
      "rating_method": "sequential_elo",
      "raw_elo": 1356.3901100732774,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.423065582541604,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5:3bb27dbc092c7ff2",
      "capped_draws": 47,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 47,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-05T05:19:06Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1377.804308515359,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.220595380503127,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 148,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:thinkingmachines-inkling-small:f1451a0a6af20650",
      "capped_draws": 131,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "draws": 131,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-09-10T04:15:56Z",
      "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": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1360.8178075609835,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.00987507357398,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 588,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-5-flash-lite:55634764b9427e4e",
      "capped_draws": 438,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 198,
      "draws": 438,
      "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": 126,
      "max_score": null,
      "measured_at": "2026-09-10T11:10:23Z",
      "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": 588,
      "rating_method": "sequential_elo",
      "raw_elo": 1350.9578409877,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.974528845713063,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 128,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:inception-mercury-2-5-preview:f07bc2e66f8341c5",
      "capped_draws": 117,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "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": "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": 6,
      "max_score": null,
      "measured_at": "2026-09-10T05:32:58Z",
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1361.0186166921785,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.802527118305367,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 551,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:meituan-longcat-2-0:bed5035a5082adf8",
      "capped_draws": 193,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 195,
      "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": "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": 265,
      "max_score": null,
      "measured_at": "2026-09-10T09:56:44Z",
      "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": 551,
      "rating_method": "sequential_elo",
      "raw_elo": 1348.152961397977,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.64483119159765,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 126,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:z-ai-glm-5-3-flash:6bc93e3f26e0f0e5",
      "capped_draws": 106,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 106,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-09-10T05:33:15Z",
      "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": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.5561479367261,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.64215239242983,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-5-flash:e1e7937be001cd2a",
      "capped_draws": 111,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "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",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-09-10T11:08:37Z",
      "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": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1358.2869226844339,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.52508073799289,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 273,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:thinkingmachines-inkling:b27963da4b6944f2",
      "capped_draws": 184,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "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": "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": 65,
      "max_score": null,
      "measured_at": "2026-09-10T03:30:40Z",
      "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": 273,
      "rating_method": "sequential_elo",
      "raw_elo": 1346.4972068552136,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.482619661848684,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 126,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:bytedance-seed-seed-2-0-code:e037862ab5c7ecb3",
      "capped_draws": 116,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 116,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:39Z",
      "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": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1356.9501384467774,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.40177753232075,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:openai-gpt-oss-120b:7e4ecfa424847773",
      "capped_draws": 112,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "draws": 112,
      "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": 14,
      "max_score": null,
      "measured_at": "2026-09-10T00:23:02Z",
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1356.0821010691934,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.347189462445694,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 2
    },
    {
      "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": 60,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-05T04:28:47Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1386.7126894336147,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.197441065976513,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 40.59014098717226,
      "unilateral_faults": null,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 229,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4:cea8a68bd875deb9",
      "capped_draws": 150,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 87,
      "draws": 150,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:11Z",
      "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": 229,
      "rating_method": "sequential_elo",
      "raw_elo": 1344.405660747203,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.08581983351418,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:45ec16f47504b5f5",
      "capped_draws": 109,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": "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": 6,
      "max_score": null,
      "measured_at": "2026-09-10T11:04:53Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1353.4712157354127,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.054798702264524,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:meta-muse-glimmer-30b:20d2aea9e268d0ef",
      "capped_draws": 111,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": "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": 6,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:40Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1353.3431681451975,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.042987762318226,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 570,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-5-flash-lite:0bab1c3ea19c7cb7",
      "capped_draws": 436,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 197,
      "draws": 436,
      "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": 107,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:31Z",
      "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": 570,
      "rating_method": "sequential_elo",
      "raw_elo": 1339.9247736299953,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.923559089613434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:z-ai-glm-5-2:20c65e2b7513d4b4",
      "capped_draws": 107,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 107,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:11Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1349.1858370718082,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.65952105621167,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 284,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:o3:29970c6bc7db3c37",
      "capped_draws": 208,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 208,
      "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": 64,
      "max_score": null,
      "measured_at": "2026-09-10T07:32:27Z",
      "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": 284,
      "rating_method": "sequential_elo",
      "raw_elo": 1336.0753658355584,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.564760696036405,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-flash:04d7da5a4f2e2af2",
      "capped_draws": 81,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": "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": 32,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:06Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1347.1953188706636,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.475918296517147,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-8-27b:3dc939e9daa83d91",
      "capped_draws": 101,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": "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": 16,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:09Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1346.2937799317099,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.392761540116325,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:stealth-ox-alpha:dfb3dd7361cfa1a2",
      "capped_draws": 213,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 124,
      "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": "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": 28,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:20Z",
      "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": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1345.8798117191247,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.354577661057732,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-luna:29e28a5adce9180a",
      "capped_draws": 148,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 148,
      "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": 50,
      "max_score": null,
      "measured_at": "2026-09-10T09:56:44Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1337.1606904094851,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.298255599085287,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:meta-muse-glimmer-30b:085624a1bd2a3883",
      "capped_draws": 110,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 110,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:12Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1342.896074063688,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.079361655784513,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 276,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:thinkingmachines-inkling:281eafa14f6ff011",
      "capped_draws": 195,
      "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": "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": 78,
      "max_score": null,
      "measured_at": "2026-09-10T11:08:22Z",
      "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": 276,
      "rating_method": "sequential_elo",
      "raw_elo": 1330.6232524994457,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.03053007285857,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:meta-muse-glimmer-30b:a614a905445f79d1",
      "capped_draws": 112,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": "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": 5,
      "max_score": null,
      "measured_at": "2026-09-10T11:05:42Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1341.382151499178,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.93971944570675,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 268,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-5-flash-lite:5943a501fa6113ab",
      "capped_draws": 200,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 91,
      "draws": 200,
      "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": 55,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:31Z",
      "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": 268,
      "rating_method": "sequential_elo",
      "raw_elo": 1326.4900962723918,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.616570657339402,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 320,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-4-5:9f0371e603fb81bd",
      "capped_draws": 194,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 194,
      "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": 99,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:52Z",
      "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": 320,
      "rating_method": "sequential_elo",
      "raw_elo": 1321.2243425653037,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.32111670246394,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:z-ai-glm-5-3-flash:1540ade2fda6b881",
      "capped_draws": 110,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 110,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:10Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1328.7367936612352,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.773328404903395,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:inception-mercury-2-5-preview:ff9c957a999941a2",
      "capped_draws": 95,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 95,
      "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": 26,
      "max_score": null,
      "measured_at": "2026-09-10T11:05:37Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1324.9158440579301,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.420889079597504,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:ibm-granite-granite-4-2-8b:49a29e6f1bedcd1d",
      "capped_draws": 105,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": "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": 19,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:08Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1318.9419863684932,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 21.86986836691461,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:openai-gpt-oss-120b:07d17099885c6bdb",
      "capped_draws": 112,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": "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": 12,
      "max_score": null,
      "measured_at": "2026-09-10T11:05:48Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1314.8381985720714,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 21.491340421683823,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:stepfun-step-3-7-flash:b2de164dfb65fa47",
      "capped_draws": 192,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 96,
      "draws": 192,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:38Z",
      "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": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1296.7353446789812,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.829015374383967,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-5:35035a0b78826dbc",
      "capped_draws": 40,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 40,
      "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": 28,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:45Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1318.701113128925,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.768995001529465,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:z-ai-glm-5-2:4571486d5f3c5826",
      "capped_draws": 97,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": "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": 27,
      "max_score": null,
      "measured_at": "2026-09-10T11:10:18Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1292.9782948203483,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 19.475011883132844,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:z-ai-glm-5-3:9e30a36ab00bd740",
      "capped_draws": 86,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": "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": 38,
      "max_score": null,
      "measured_at": "2026-09-10T11:09:46Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1286.0804835275962,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 18.83876691512749,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:d0b5b92265541548",
      "capped_draws": 102,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 102,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-09-10T11:09:39Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1285.5605334671657,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 18.79080741094235,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-luna:e05ef4cc93414f96",
      "capped_draws": 164,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 164,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-09-10T11:08:37Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1267.149087461531,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.840478169825914,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-5:32918e3c3e0fca83",
      "capped_draws": 33,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 33,
      "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": 33,
      "max_score": null,
      "measured_at": "2026-07-31T03:36:31Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1285.2690176663273,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.62225691914307,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:z-ai-glm-5-3-flash:22cd36959459fbdd",
      "capped_draws": 81,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 81,
      "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": 40,
      "max_score": null,
      "measured_at": "2026-09-10T11:08:42Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1231.9861064630934,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 13.849173297099911,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-5-flash:79befaaad7974375",
      "capped_draws": 75,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 75,
      "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": 48,
      "max_score": null,
      "measured_at": "2026-09-10T11:09:43Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1220.0518609352368,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.748374312932619,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:nex-agi-nex-n2-pro:a8c61d4550659ad0",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "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": "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": 51,
      "max_score": null,
      "measured_at": "2026-08-05T02:33:48Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1174.3876372219918,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 7.328898964258992,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 206,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-luna:15a0f0a09f9eb8e5",
      "capped_draws": 41,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "draws": 41,
      "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": 153,
      "max_score": null,
      "measured_at": "2026-09-10T10:00:52Z",
      "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": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1073.865967034946,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-6-astra:ae6ec4a095f6b7a9",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_standard_estimate": 24
        },
        "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": 15.613270000000002
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 41,
      "draws": 290,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T11:11:15Z",
      "losses": 319,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 50.47588011557324,
      "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": 2857,
      "rating_method": "sequential_elo",
      "raw_elo": 1907.2745066765685,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 81.90889466396655,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 2248
    },
    {
      "admitted_plugins": 27,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:claude-fable-5-1:ff8eddc4d6e61a06",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 27,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_list_price_estimate": 30
        },
        "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": 42,
      "draws": 251,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T11:10:23Z",
      "losses": 427,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 44.553723611281114,
      "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": 3228,
      "rating_method": "sequential_elo",
      "raw_elo": 1909.4755209549166,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 81.11701473119925,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 2550
    },
    {
      "admitted_plugins": 41,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:claude-opus-5:1cfce33a4d60e796",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 41,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_list_price_estimate": 48
        },
        "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": 33.78345
      },
      "codegen_evaluated_cells": 48,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 58,
      "draws": 411,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T04:58:29Z",
      "losses": 488,
      "max_score": 85.05036844756516,
      "measured_at": null,
      "min_score": 36.957881306791684,
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2797,
      "rating_method": "sequential_elo",
      "raw_elo": 1743.1325141977638,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 59.77996525764912,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1898
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5-6-sol:e3cbd9a07a4054c5",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_standard_estimate": 25
        },
        "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": 44,
      "draws": 779,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T11:12:01Z",
      "losses": 1411,
      "max_score": 95.50333681723484,
      "measured_at": null,
      "min_score": 13.272080636024716,
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 5037,
      "rating_method": "sequential_elo",
      "raw_elo": 1673.0641291849886,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 58.73272306177361,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 2847
    },
    {
      "admitted_plugins": 23,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:z-ai-glm-5-3:3abeca073b191728",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 23,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 26
        },
        "evidence_basis": "Provider-reported",
        "max": 0.5256212,
        "mean": 0.19965798354166664,
        "median": 0.1553977,
        "min": 0.0217974,
        "recorded_attempt_count": 26,
        "run_count": 24,
        "total": 4.791791604999999
      },
      "codegen_evaluated_cells": 23,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 625,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T11:07:59Z",
      "losses": 821,
      "max_score": 98.77394998739801,
      "measured_at": null,
      "min_score": 10.263403044539475,
      "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": 2845,
      "rating_method": "sequential_elo",
      "raw_elo": 1692.1776017448938,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 57.782713884825235,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1399
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:claude-fable-5:d7f80fef92b21cfc",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_list_price_estimate": 24
        },
        "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": 43,
      "draws": 686,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T11:07:59Z",
      "losses": 1009,
      "max_score": 85.88512253636422,
      "measured_at": null,
      "min_score": 6.646568053595592,
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3021,
      "rating_method": "sequential_elo",
      "raw_elo": 1631.0986898133094,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 51.4600732684003,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1326
    },
    {
      "admitted_plugins": 23,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5-4:94ba2258c434ca13",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 23,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_standard_estimate": 27
        },
        "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": 15.1879375
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 1407,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T11:11:29Z",
      "losses": 1379,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 8.247425935777672,
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 4952,
      "rating_method": "sequential_elo",
      "raw_elo": 1625.504606811982,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 48.791985606250556,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 2166
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:x-ai-grok-4-6:d44a6fc0597186af",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 27
        },
        "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": 44,
      "draws": 876,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T11:06:41Z",
      "losses": 1071,
      "max_score": 82.4874985834472,
      "measured_at": null,
      "min_score": 9.318441010342715,
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3122,
      "rating_method": "sequential_elo",
      "raw_elo": 1582.5452258317468,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 47.21221876040718,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1175
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:google-gemini-3-8-flash:e15e99a40699c049",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_list_price_estimate": 25
        },
        "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": 1.9756462499999998
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 753,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T11:10:07Z",
      "losses": 1170,
      "max_score": 79.59975068636147,
      "measured_at": null,
      "min_score": 6.964348588339904,
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3102,
      "rating_method": "sequential_elo",
      "raw_elo": 1579.3155732964753,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 46.76433524376487,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1179
    },
    {
      "admitted_plugins": 22,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:claude-opus-4-8:4f9a7620e16b0214",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 22,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_list_price_estimate": 25
        },
        "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": 33,
      "draws": 414,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T03:49:27Z",
      "losses": 383,
      "max_score": 70.79490986212144,
      "measured_at": null,
      "min_score": 10.886852859373011,
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1488,
      "rating_method": "sequential_elo",
      "raw_elo": 1600.8695174992667,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 46.757715568855076,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 691
    },
    {
      "admitted_plugins": 22,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:meta-muse-spark-1-3:a74ca6e1542043ee",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 22,
        "cell_count": 23,
        "cost_basis_counts": {
          "provider_reported": 24
        },
        "evidence_basis": "Provider-reported",
        "max": 0.273243,
        "mean": 0.0832670543478261,
        "median": 0.04626,
        "min": 0.0,
        "recorded_attempt_count": 24,
        "run_count": 23,
        "total": 1.9151422500000004
      },
      "codegen_evaluated_cells": 22,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 665,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T11:12:08Z",
      "losses": 1029,
      "max_score": 79.56504037106075,
      "measured_at": null,
      "min_score": 10.355871463342384,
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 2813,
      "rating_method": "sequential_elo",
      "raw_elo": 1573.0834711396174,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 45.75435855307182,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1119
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:x-ai-grok-4-5:36b95fae38939a0e",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 34
        },
        "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": 1.6998544
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 63,
      "draws": 1249,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T10:39:02Z",
      "losses": 1531,
      "max_score": 81.02581011754175,
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 5025,
      "rating_method": "sequential_elo",
      "raw_elo": 1572.0858149384221,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 45.595722368714796,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 2245
    },
    {
      "admitted_plugins": 22,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5-5:88a334b93dec2dd0",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 22,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_standard_estimate": 26
        },
        "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": 26.56635
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 34,
      "draws": 551,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T05:23:57Z",
      "losses": 396,
      "max_score": 82.05925729033785,
      "measured_at": null,
      "min_score": 13.936024036303673,
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1538,
      "rating_method": "sequential_elo",
      "raw_elo": 1592.0071770037957,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 45.48623392985055,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 591
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:z-ai-glm-5-3-flash:9aca75dd26e8e2c9",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 28
        },
        "evidence_basis": "Provider-reported",
        "max": 0.02871725,
        "mean": 0.008139411458333334,
        "median": 0.005035225,
        "min": 0.001111625,
        "recorded_attempt_count": 28,
        "run_count": 24,
        "total": 0.195345875
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 892,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T10:37:14Z",
      "losses": 1020,
      "max_score": 75.69077551550029,
      "measured_at": null,
      "min_score": 8.088342646823264,
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2995,
      "rating_method": "sequential_elo",
      "raw_elo": 1541.4025169879208,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 45.44850498009302,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1083
    },
    {
      "admitted_plugins": 23,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:tencent-hy4-preview:64b986c8d9e0b166",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 23,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 28
        },
        "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": 44,
      "draws": 892,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T11:05:01Z",
      "losses": 1020,
      "max_score": 86.09465836643398,
      "measured_at": null,
      "min_score": 7.401997425923536,
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3078,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.9586294344847,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 45.08459185672779,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1166
    },
    {
      "admitted_plugins": 42,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:google-gemini-3-6-flash:0604b840849e2584",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 42,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 126
        },
        "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": 12.701101349999997
      },
      "codegen_evaluated_cells": 48,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 63,
      "draws": 2885,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T10:59:04Z",
      "losses": 3367,
      "max_score": 85.6020891745296,
      "measured_at": null,
      "min_score": 6.451833831046862,
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 10397,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.324999304988,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 42.75242302612431,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 4145
    },
    {
      "admitted_plugins": 21,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:moonshotai-kimi-k3:71508839738a1256",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 21,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 40
        },
        "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": 63,
      "draws": 1825,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T10:37:23Z",
      "losses": 1980,
      "max_score": 89.21089685186311,
      "measured_at": null,
      "min_score": 6.485222218768579,
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 5878,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.2417586813356,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 41.41431270485983,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 2073
    },
    {
      "admitted_plugins": 79,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:stealth-ox-alpha:ffd76b5b23c55ff5",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 79,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 112
        },
        "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": 44,
      "draws": 2838,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T11:12:08Z",
      "losses": 3854,
      "max_score": 63.32717677815119,
      "measured_at": null,
      "min_score": 10.84501570624497,
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 10469,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.2340758706835,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 41.352237179328434,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 3777
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5:c745ec618c97d50e",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 21,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_standard_estimate": 31
        },
        "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": 4.4559187499999995
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 303,
      "eligibility_flag": false,
      "entry_count": 15,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 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": [
        "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": "2026-08-05T05:19:06Z",
      "losses": 336,
      "max_score": 65.51337979360243,
      "measured_at": null,
      "min_score": 12.515897799774466,
      "model_code_failure_rate": 0.0625,
      "model_code_failures": 1,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 998,
      "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",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 40.726675100434214,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 359
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:qwen-qwen3-8-2-4t-a95b:c1f7759c0d0f3c47",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_list_price_estimate": 27
        },
        "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": 5.4708879999999995
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 976,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T10:47:44Z",
      "losses": 1052,
      "max_score": 85.08829766988379,
      "measured_at": null,
      "min_score": 8.285036037313507,
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3141,
      "rating_method": "sequential_elo",
      "raw_elo": 1513.0862427746608,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 40.564939321453636,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1113
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:claude-opus-4-5:eebfed4239db54b7",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 39,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_list_price_estimate": 41
        },
        "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": 11.203785000000002
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 63,
      "draws": 1420,
      "eligibility_flag": false,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-10T11:05:01Z",
      "losses": 1735,
      "max_score": 59.105299689263475,
      "measured_at": null,
      "min_score": 4.775250900350241,
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 4990,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.4000182082762,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 39.67603526846738,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1835
    },
    {
      "admitted_plugins": 17,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:meta-muse-spark-1-2:621e8d10c5a4ba0a",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 17,
        "cell_count": 18,
        "cost_basis_counts": {
          "provider_reported": 20
        },
        "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": 44,
      "draws": 846,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T11:08:49Z",
      "losses": 1511,
      "max_score": 64.21230002498487,
      "measured_at": null,
      "min_score": 3.906687867060584,
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 3688,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.3663028961287,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 39.288704593155906,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1331
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:xiaomi-mimo-v2-5-pro:2975b362b8c181f7",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 15,
        "cost_basis_counts": {
          "provider_reported": 27
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.2996388,
        "mean": 0.08564151856,
        "median": 0.0495450162,
        "min": 0.0057139812,
        "recorded_attempt_count": 27,
        "run_count": 15,
        "total": 1.2846227783999995
      },
      "codegen_evaluated_cells": 15,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 32,
      "draws": 196,
      "eligibility_flag": false,
      "entry_count": 11,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 0.26666666666666666,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_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",
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:11:01Z",
      "losses": 318,
      "max_score": 70.02330483752023,
      "measured_at": null,
      "min_score": 16.473094673491183,
      "model_code_failure_rate": 0.2,
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 836,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 8,
      "repaired_rate": 0.5333333333333333,
      "results_cut_id": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 38.47985425221955,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 322
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:qwen-qwen3-7-max:73d75d50d9e31317",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 24
        },
        "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": 33,
      "draws": 367,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T05:35:11Z",
      "losses": 332,
      "max_score": 71.61968219996771,
      "measured_at": null,
      "min_score": 12.895585775886488,
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1038,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 38.46573713577355,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 339
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:moonshotai-kimi-k2-7-code:9a2f1affb126d4fe",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "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": 32,
      "draws": 143,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T05:26:41Z",
      "losses": 159,
      "max_score": 55.31987902290327,
      "measured_at": null,
      "min_score": 15.971215353629413,
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 492,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 38.247912032324855,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 190
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:google-gemini-3-5-flash:3c7e1f4e41b6571d",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 30,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_list_price_estimate": 32,
          "provider_reported": 14
        },
        "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": 44,
      "draws": 937,
      "eligibility_flag": false,
      "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-3.5-flash",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T11:08:39Z",
      "losses": 1169,
      "max_score": 82.02311872112153,
      "measured_at": null,
      "min_score": 8.860426297576485,
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 3093,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.4015736080792,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 38.210250252668835,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 987
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:qwen-qwen3-8-max:65623d2d6810d868",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 30
        },
        "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": 44,
      "draws": 1099,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T11:05:04Z",
      "losses": 1205,
      "max_score": 88.76990902930297,
      "measured_at": null,
      "min_score": 6.07109411954341,
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3376,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.848731682721,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 37.75785336349297,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1072
    },
    {
      "admitted_plugins": 22,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:deepseek-deepseek-v4-pro:bf80275c6345b0be",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 22,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 35
        },
        "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": 1.4885651789640004
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 919,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T10:50:08Z",
      "losses": 1001,
      "max_score": 70.6332524935784,
      "measured_at": null,
      "min_score": 8.46888583743832,
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2901,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.109012137743,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 37.167822693466015,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 981
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:qwen-qwen3-8-flash:c2223bad538b65f0",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 22
        },
        "evidence_basis": "Provider-reported",
        "max": 0.061982706,
        "mean": 0.020562389374999997,
        "median": 0.015992453,
        "min": 0.0021123,
        "recorded_attempt_count": 22,
        "run_count": 16,
        "total": 0.32899823
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 781,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T11:08:50Z",
      "losses": 757,
      "max_score": 72.14023042347958,
      "measured_at": null,
      "min_score": 8.345895178371906,
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 2114,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 37.12481531751189,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 576
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:claude-sonnet-5:4d974e631781e828",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_list_price_estimate": 24
        },
        "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": 44,
      "draws": 1458,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T10:49:31Z",
      "losses": 1850,
      "max_score": 74.33339438299416,
      "measured_at": null,
      "min_score": 7.484704864315055,
      "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": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 5088,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.2602101792713,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 36.77264902241199,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1780
    },
    {
      "admitted_plugins": 23,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5-6-terra:7f7e7232e01df2a7",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 23,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_standard_estimate": 28
        },
        "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": 44,
      "draws": 1028,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T11:12:01Z",
      "losses": 1129,
      "max_score": 69.43940999034174,
      "measured_at": null,
      "min_score": 9.955451026536553,
      "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": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3121,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.3466433964543,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 36.269658792302785,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 964
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-4-1:5e8f4f6f136095e6",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 11
        },
        "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": 0.45756399999999997
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 196,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T05:41:31Z",
      "losses": 198,
      "max_score": 55.88308492443146,
      "measured_at": null,
      "min_score": 11.682283349084813,
      "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": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 571,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 35.80056693008479,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 177
    },
    {
      "admitted_plugins": 22,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:deepseek-deepseek-v4-pro-0813:8cf52f82ea7b1615",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 22,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 31
        },
        "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": 2.3773764379599998
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 975,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T11:10:07Z",
      "losses": 1066,
      "max_score": 74.8155896456324,
      "measured_at": null,
      "min_score": 0.0,
      "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": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2998,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.2469512213218,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 35.55020961791368,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 957
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:x-ai-grok-build-0-1:f893c31f7fbbffea",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "evidence_basis": "Provider-reported",
        "max": 0.07439860000000001,
        "mean": 0.060660574999999994,
        "median": 0.0565846,
        "min": 0.0485456,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 0.48528459999999995
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 32,
      "draws": 230,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T05:34:43Z",
      "losses": 205,
      "max_score": 65.57660382357807,
      "measured_at": null,
      "min_score": 12.336802440575292,
      "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": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 620,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 35.20852304594772,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 185
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5-4-mini:d159cf528f6e5fa3",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 17,
        "cost_basis_counts": {
          "estimated": 2,
          "local_standard_estimate": 22
        },
        "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": 5.168810400000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 432,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T06:55:18Z",
      "losses": 387,
      "max_score": 56.015466910410275,
      "measured_at": null,
      "min_score": 12.418449045966476,
      "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": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1175,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 35.18305718375038,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 356
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-4-1-nano:802f6446e1922474",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 1,
        "cell_count": 1,
        "cost_basis_counts": {
          "estimated": 1,
          "local_standard_estimate": 1
        },
        "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": 45,
      "draws": 65,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T01:47:37Z",
      "losses": 103,
      "max_score": 35.18099307381629,
      "measured_at": null,
      "min_score": 35.18099307381629,
      "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": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 278,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 35.18099307381629,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 110
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5-4-nano:ace24c78c399f116",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 17,
        "cost_basis_counts": {
          "estimated": 2,
          "local_standard_estimate": 55
        },
        "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": 1.0821379
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 34,
      "draws": 436,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T06:55:07Z",
      "losses": 680,
      "max_score": 60.07944202124918,
      "measured_at": null,
      "min_score": 12.179369637744257,
      "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": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1742,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 34.67569980949435,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 29,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:o3:561d98a4c5ea6b70",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 29,
        "cell_count": 24,
        "cost_basis_counts": {
          "estimated": 40,
          "local_standard_estimate": 29
        },
        "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": 4.201686
      },
      "codegen_evaluated_cells": 48,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 63,
      "draws": 1046,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T10:09:01Z",
      "losses": 2980,
      "max_score": 64.65603985716929,
      "measured_at": null,
      "min_score": 13.652811210043236,
      "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": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 6734,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.5008620250965,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 34.26336589604531,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 2708
    },
    {
      "admitted_plugins": 10,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:google-gemma-4-31b-it:9b5bb4ae0cfde398",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 10,
        "cell_count": 14,
        "cost_basis_counts": {
          "provider_reported": 23
        },
        "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": 34,
      "draws": 197,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T03:57:18Z",
      "losses": 341,
      "max_score": 57.095657519959566,
      "measured_at": null,
      "min_score": 24.766615824644276,
      "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": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 804,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 33.933977912569986,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 266
    },
    {
      "admitted_plugins": 32,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:z-ai-glm-5-2:8ed5b674f4d47981",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 48,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 72
        },
        "evidence_basis": "Provider-reported",
        "max": 0.39278997800000004,
        "mean": 0.09944282164861112,
        "median": 0.056673037849999996,
        "min": 0.013816857666666668,
        "recorded_attempt_count": 72,
        "run_count": 48,
        "total": 3.5146565168
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 63,
      "draws": 1576,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T11:06:45Z",
      "losses": 1551,
      "max_score": 72.14085667254591,
      "measured_at": null,
      "min_score": 3.385411727320254,
      "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": 40,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 4310,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.3744998474467,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 33.71521001940187,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1183
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:qwen-qwen3-7-plus:8997dfac4b0e4cf4",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 29
        },
        "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": 33,
      "draws": 293,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T03:48:47Z",
      "losses": 347,
      "max_score": 70.99957787144118,
      "measured_at": null,
      "min_score": 14.181701766649182,
      "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": 41,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 916,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 33.12938127623754,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 276
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:qwen-qwen3-8-27b:13806a60945d43bf",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 41
        },
        "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": 2.084028948
      },
      "codegen_evaluated_cells": 23,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 407,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T10:06:23Z",
      "losses": 690,
      "max_score": 74.97439218948013,
      "measured_at": null,
      "min_score": 18.550918857121076,
      "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": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1715,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 32.48775375004117,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 618
    },
    {
      "admitted_plugins": 13,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:tencent-hy3-preview:f0f52491401ad45b",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 13,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 25
        },
        "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": 0.041725612999999995
      },
      "codegen_evaluated_cells": 17,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 294,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T05:11:51Z",
      "losses": 297,
      "max_score": 64.07635846709539,
      "measured_at": null,
      "min_score": 7.405950095136704,
      "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": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 846,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 31.65920071627273,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 255
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5-6-luna:bcc0bd9ea9d81a91",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_standard_estimate": 25
        },
        "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": 0.33399885
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 1692,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T11:05:04Z",
      "losses": 1917,
      "max_score": 79.12179151899733,
      "measured_at": null,
      "min_score": 0.0,
      "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": 5010,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.3982984799898,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 31.53471229363161,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1401
    },
    {
      "admitted_plugins": 13,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:minimax-minimax-m3:98784e253f1f8550",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 13,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 30
        },
        "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": 33,
      "draws": 292,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T04:33:21Z",
      "losses": 442,
      "max_score": 48.5556009285104,
      "measured_at": null,
      "min_score": 5.046768034226976,
      "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": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1030,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 30.03148516557112,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 296
    },
    {
      "admitted_plugins": 13,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:stepfun-step-3-7-flash:097f668cb006b9b1",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 13,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 59
        },
        "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": 1.0000669800000002
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 60,
      "draws": 390,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T11:06:38Z",
      "losses": 806,
      "max_score": 49.98510602874532,
      "measured_at": null,
      "min_score": 15.266282350907517,
      "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": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1765,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.816040599028,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 29.41647191950841,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 569
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:xiaomi-mimo-v2-5:3140add484494bcc",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 37,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 108
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 16,
        "max": 0.0597184625,
        "mean": 0.015888486455555555,
        "median": 0.014928570933333333,
        "min": 0.0016912200000000002,
        "recorded_attempt_count": 108,
        "run_count": 56,
        "total": 0.7524538072
      },
      "codegen_evaluated_cells": 36,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 34,
      "draws": 897,
      "eligibility_flag": false,
      "entry_count": 37,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T05:41:45Z",
      "losses": 911,
      "max_score": 55.88030293196678,
      "measured_at": null,
      "min_score": 10.940010823479835,
      "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": 47,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 2540,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.3815115156615,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 29.13819034227683,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 732
    },
    {
      "admitted_plugins": 21,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:nvidia-nemotron-3-ultra-550b-a55b:32ef0b4e4a037e65",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 21,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 70
        },
        "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": 33,
      "draws": 516,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T04:29:54Z",
      "losses": 473,
      "max_score": 58.942903698869344,
      "measured_at": null,
      "min_score": 10.53671511272001,
      "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": 48,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1317,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.2543234823834,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 29.12884239004842,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 328
    },
    {
      "admitted_plugins": 28,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:deepseek-deepseek-v4-flash:bc21de560c0fa311",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 36,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 59
        },
        "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": 63,
      "draws": 1289,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T10:26:14Z",
      "losses": 1364,
      "max_score": 73.77217005426371,
      "measured_at": null,
      "min_score": 2.2211281793648086,
      "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": 49,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3694,
      "rating_method": "sequential_elo",
      "raw_elo": 1399.226210427795,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 28.921609624469905,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1041
    },
    {
      "admitted_plugins": 22,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:bytedance-seed-seed-2-0-code:ee2aa4f5e2c2d7e9",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 22,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 34
        },
        "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": 1.001483
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 911,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T11:06:39Z",
      "losses": 1123,
      "max_score": 74.84224837474918,
      "measured_at": null,
      "min_score": 5.142930493219368,
      "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": 50,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2831,
      "rating_method": "sequential_elo",
      "raw_elo": 1370.0203453495526,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 28.357130200643297,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 797
    },
    {
      "admitted_plugins": 23,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:poolside-laguna-s-2-1:d976839d396cf2ac",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 23,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 68
        },
        "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": 63,
      "draws": 1731,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T10:57:42Z",
      "losses": 1527,
      "max_score": 54.10090278289114,
      "measured_at": null,
      "min_score": 9.449979970240136,
      "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": 51,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 4196,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 28.11776160671457,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 938
    },
    {
      "admitted_plugins": 43,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:google-gemini-3-5-flash-lite:8b44dc7bcfc24a61",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 43,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 132
        },
        "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": 1.8519748999999999
      },
      "codegen_evaluated_cells": 48,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 63,
      "draws": 3522,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T11:06:39Z",
      "losses": 4506,
      "max_score": 65.89914757897805,
      "measured_at": null,
      "min_score": 9.623986038775216,
      "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": 52,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 10860,
      "rating_method": "sequential_elo",
      "raw_elo": 1363.611864553113,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 27.647134655398105,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 2832
    },
    {
      "admitted_plugins": 26,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:meituan-longcat-2-0:89d5714ff2045319",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 26,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 108
        },
        "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": 1.6004064599999999
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 63,
      "draws": 1277,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T10:39:01Z",
      "losses": 2011,
      "max_score": 44.89316223345493,
      "measured_at": null,
      "min_score": 5.565460776989309,
      "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": 53,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 4404,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 27.3505040481569,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1116
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:nex-agi-nex-n2-pro:6bc8ed75bf8e498c",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 53
        },
        "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": 3.4057992500000003
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 265,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T05:35:20Z",
      "losses": 360,
      "max_score": 60.77934776395481,
      "measured_at": null,
      "min_score": 7.328898964258992,
      "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": 54,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 844,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 26.812441583286457,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 219
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:cohere-north-mini-code:c4cb188aa646b3a5",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 11,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 45
        },
        "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": 34,
      "draws": 303,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 388,
      "max_score": 49.11080098947388,
      "measured_at": null,
      "min_score": 21.93263264971003,
      "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": 55,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 910,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 26.77319662715879,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 219
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:google-gemini-3-1-flash-lite:cac04a72708dea25",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 50
        },
        "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": 0.348093
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 296,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T05:18:42Z",
      "losses": 591,
      "max_score": 45.56327909407335,
      "measured_at": null,
      "min_score": 13.765200753063453,
      "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": 56,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1149,
      "rating_method": "sequential_elo",
      "raw_elo": 1260.0777325626234,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 25.371913023508757,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 262
    },
    {
      "admitted_plugins": 21,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:meta-muse-glimmer-30b:e28d1f44c6bb63d9",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 21,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 34
        },
        "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": 43,
      "draws": 1099,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T10:39:06Z",
      "losses": 913,
      "max_score": 49.03370945933072,
      "measured_at": null,
      "min_score": 6.990073492948425,
      "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": 57,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2606,
      "rating_method": "sequential_elo",
      "raw_elo": 1349.5450396129843,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 25.30366060580623,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 594
    },
    {
      "admitted_plugins": 21,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:openai-gpt-oss-120b:6f4e74d7b4b7c6e2",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 21,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 33
        },
        "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": 44,
      "draws": 1078,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T10:39:05Z",
      "losses": 949,
      "max_score": 53.690628075980555,
      "measured_at": null,
      "min_score": 9.761584645888398,
      "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": 2647,
      "rating_method": "sequential_elo",
      "raw_elo": 1343.8843204600316,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 24.94489181914878,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 27,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:thinkingmachines-inkling:e81035030b907e0c",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 27,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 145
        },
        "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": 63,
      "draws": 1559,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T10:39:04Z",
      "losses": 2099,
      "max_score": 60.57535339573391,
      "measured_at": null,
      "min_score": 9.050334687326071,
      "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": 59,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 4710,
      "rating_method": "sequential_elo",
      "raw_elo": 1345.7003792940125,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 24.428911562338516,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1052
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:thinkingmachines-inkling-small:da2ad9b9e5446839",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 43
        },
        "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": 44,
      "draws": 1317,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T10:54:12Z",
      "losses": 1347,
      "max_score": 54.086740109183,
      "measured_at": null,
      "min_score": 0.0,
      "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": 60,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3436,
      "rating_method": "sequential_elo",
      "raw_elo": 1317.6730815169108,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 23.048206727876472,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 772
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:inclusionai-ling-3-0-flash:e189ecaee6c08cd0",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 92
        },
        "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": 63,
      "draws": 1000,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 1142,
      "max_score": 43.412761651647685,
      "measured_at": null,
      "min_score": 6.242872745526706,
      "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": 61,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 2686,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 19.669893064192422,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 544
    },
    {
      "admitted_plugins": 17,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:inception-mercury-2-5-preview:3aa5fb5362d4d302",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 17,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 37
        },
        "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": 0.02831297
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 896,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T10:39:02Z",
      "losses": 840,
      "max_score": 39.11032563550241,
      "measured_at": null,
      "min_score": 6.865539546300709,
      "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": 62,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2080,
      "rating_method": "sequential_elo",
      "raw_elo": 1321.1201709858635,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 18.426180718347165,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 344
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:ibm-granite-granite-4-2-8b:49adcc62fd4c0638",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 3,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 54
        },
        "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": 0.09619380000000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 206,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T11:06:08Z",
      "losses": 167,
      "max_score": 21.86986836691461,
      "measured_at": null,
      "min_score": 0.0,
      "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": 63,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 380,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 9.90893025148373,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 7
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 953,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-6-astra:dd3177afdee2bb2a",
      "capped_draws": 9,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "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": 79.44415234078821,
      "contributing_entrants": null,
      "distinct_rated_opponents": 40,
      "draws": 115,
      "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": "2026-09-10T11:11:15Z",
      "losses": 116,
      "max_score": 95.94419593771026,
      "measured_at": null,
      "min_score": 57.36356914969686,
      "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": 953,
      "rating_method": "sequential_elo",
      "raw_elo": 1876.6272960247202,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 79.44415234078821,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 722
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 954,
      "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
        },
        "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": 77.18422949193521,
      "contributing_entrants": null,
      "distinct_rated_opponents": 41,
      "draws": 82,
      "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": "2026-09-10T11:10:23Z",
      "losses": 171,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 52.70456806499455,
      "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": 954,
      "rating_method": "sequential_elo",
      "raw_elo": 1872.6782855747924,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 77.18422949193521,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 956,
      "canonical_public_row_identity": "publication-row.v1:balanced:claude-opus-5:f836f90d8fb9ff19",
      "capped_draws": 15,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 16
        },
        "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": 7.138875000000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 62.639402761935784,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 123,
      "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": "2026-08-05T05:35:16Z",
      "losses": 154,
      "max_score": 77.13223675647313,
      "measured_at": null,
      "min_score": 37.38045751660635,
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 956,
      "rating_method": "sequential_elo",
      "raw_elo": 1760.541512421418,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 60.582839053113815,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 679
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1008,
      "canonical_public_row_identity": "publication-row.v1:balanced:z-ai-glm-5-3:ebf51d85881ca5b8",
      "capped_draws": 61,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "evidence_basis": "Provider-reported",
        "max": 0.23469315999999998,
        "mean": 0.156944395,
        "median": 0.1664265,
        "min": 0.07192,
        "recorded_attempt_count": 10,
        "run_count": 8,
        "total": 1.2555551600000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 59.35550035157464,
      "contributing_entrants": null,
      "distinct_rated_opponents": 42,
      "draws": 176,
      "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": "2026-09-10T11:09:42Z",
      "losses": 321,
      "max_score": 95.8308881823799,
      "measured_at": null,
      "min_score": 24.766285822102056,
      "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": 1007,
      "rating_method": "sequential_elo",
      "raw_elo": 1687.8803688315882,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 59.35550035157464,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 990,
      "canonical_public_row_identity": "publication-row.v1:balanced:x-ai-grok-4-6:69246fd982959de2",
      "capped_draws": 34,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "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": 56.21231506536722,
      "contributing_entrants": null,
      "distinct_rated_opponents": 42,
      "draws": 196,
      "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": "2026-09-10T11:09:42Z",
      "losses": 307,
      "max_score": 74.21271794604775,
      "measured_at": null,
      "min_score": 18.364695347029407,
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 984,
      "rating_method": "sequential_elo",
      "raw_elo": 1688.994816387265,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 56.21231506536722,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 481
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1626,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-6-sol:60281ce94ea88014",
      "capped_draws": 84,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "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": 56.18273720189021,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 251,
      "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": "2026-09-10T11:07:47Z",
      "losses": 516,
      "max_score": 76.41507877251388,
      "measured_at": null,
      "min_score": 34.76336759556245,
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1625,
      "rating_method": "sequential_elo",
      "raw_elo": 1636.494237325968,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 56.18273720189021,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1027,
      "canonical_public_row_identity": "publication-row.v1:balanced:meta-muse-spark-1-3:b928c7e11b83bab6",
      "capped_draws": 11,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "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": 51.9876898864305,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 146,
      "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": "2026-09-10T11:12:08Z",
      "losses": 432,
      "max_score": 76.70363100762701,
      "measured_at": null,
      "min_score": 31.93233314474059,
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1019,
      "rating_method": "sequential_elo",
      "raw_elo": 1627.6642228917171,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 51.9876898864305,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 441
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 954,
      "canonical_public_row_identity": "publication-row.v1:balanced:claude-fable-5:4fee988c3b8ad119",
      "capped_draws": 16,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "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": 49.646949204317174,
      "contributing_entrants": null,
      "distinct_rated_opponents": 41,
      "draws": 197,
      "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": "2026-09-10T11:07:59Z",
      "losses": 344,
      "max_score": 77.10732678766597,
      "measured_at": null,
      "min_score": 10.636544202241724,
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 954,
      "rating_method": "sequential_elo",
      "raw_elo": 1620.6537941577335,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 49.646949204317174,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 413
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1022,
      "canonical_public_row_identity": "publication-row.v1:balanced:z-ai-glm-5-3-flash:1cd9221832b4ca47",
      "capped_draws": 110,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "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": 48.74706488440559,
      "contributing_entrants": null,
      "distinct_rated_opponents": 42,
      "draws": 292,
      "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": "2026-09-10T11:06:10Z",
      "losses": 336,
      "max_score": 75.69077551550029,
      "measured_at": null,
      "min_score": 13.629201190774216,
      "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": 1015,
      "rating_method": "sequential_elo",
      "raw_elo": 1594.6691703367667,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 48.74706488440559,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 387
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 656,
      "canonical_public_row_identity": "publication-row.v1:balanced:x-ai-grok-4-5:9ade9c53df23b855",
      "capped_draws": 9,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "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": 47.885604863809434,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 146,
      "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": "2026-08-05T05:42:30Z",
      "losses": 173,
      "max_score": 75.36004018487888,
      "measured_at": null,
      "min_score": 15.084858110615464,
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 654,
      "rating_method": "sequential_elo",
      "raw_elo": 1608.1090208290418,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 47.885604863809434,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 335
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1051,
      "canonical_public_row_identity": "publication-row.v1:balanced:qwen-qwen3-8-flash:5a72b22afc48c9d2",
      "capped_draws": 156,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "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": 47.54012688882566,
      "contributing_entrants": null,
      "distinct_rated_opponents": 42,
      "draws": 346,
      "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": "2026-09-10T11:11:42Z",
      "losses": 337,
      "max_score": 72.14023042347958,
      "measured_at": null,
      "min_score": 19.25382084260791,
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1050,
      "rating_method": "sequential_elo",
      "raw_elo": 1597.9463423744303,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 47.54012688882566,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 367
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1052,
      "canonical_public_row_identity": "publication-row.v1:balanced:google-gemini-3-8-flash:9fd2f22238c82925",
      "capped_draws": 133,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "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": 47.189592263291324,
      "contributing_entrants": null,
      "distinct_rated_opponents": 42,
      "draws": 335,
      "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": "2026-09-10T11:10:07Z",
      "losses": 322,
      "max_score": 75.82334053498934,
      "measured_at": null,
      "min_score": 7.902824182042486,
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1046,
      "rating_method": "sequential_elo",
      "raw_elo": 1590.1142917632478,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 47.189592263291324,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 389
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 960,
      "canonical_public_row_identity": "publication-row.v1:balanced:tencent-hy4-preview:a81918b0d5baba2a",
      "capped_draws": 13,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "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": 48.51069202035984,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 178,
      "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": "2026-09-10T11:06:19Z",
      "losses": 362,
      "max_score": 86.09465836643398,
      "measured_at": null,
      "min_score": 9.230754142229273,
      "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": 960,
      "rating_method": "sequential_elo",
      "raw_elo": 1581.2308295981145,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 46.917999173685125,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 420
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1762,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-4:91029345b4b373cd",
      "capped_draws": 186,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "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": 46.19996042414856,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 598,
      "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": "2026-09-10T11:06:20Z",
      "losses": 442,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 9.48709633237125,
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1756,
      "rating_method": "sequential_elo",
      "raw_elo": 1598.3142606272136,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 46.19996042414856,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 716
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 580,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-5:fc52395a742e5644",
      "capped_draws": 91,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "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": 45.65211067782296,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 196,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": "2026-08-05T04:43:10Z",
      "losses": 155,
      "max_score": 66.31252434317867,
      "measured_at": null,
      "min_score": 23.27457919744084,
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 580,
      "rating_method": "sequential_elo",
      "raw_elo": 1579.7486408374518,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 45.65211067782296,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 229
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 2925,
      "canonical_public_row_identity": "publication-row.v1:balanced:google-gemini-3-6-flash:157bc5e3bd81a2f8",
      "capped_draws": 244,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 44
        },
        "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": 46.76079180174214,
      "contributing_entrants": null,
      "distinct_rated_opponents": 63,
      "draws": 730,
      "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": "2026-09-10T11:10:23Z",
      "losses": 807,
      "max_score": 77.74963744928857,
      "measured_at": null,
      "min_score": 6.451833831046862,
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2923,
      "rating_method": "sequential_elo",
      "raw_elo": 1600.6651747084215,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 45.225551311331834,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1386
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 496,
      "canonical_public_row_identity": "publication-row.v1:balanced:o3:9e4cf63e80682b9b",
      "capped_draws": 68,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "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": 46.63103950637711,
      "contributing_entrants": null,
      "distinct_rated_opponents": 32,
      "draws": 127,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "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": "2026-08-05T05:17:46Z",
      "losses": 152,
      "max_score": 64.65603985716929,
      "measured_at": null,
      "min_score": 22.72518278425092,
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 496,
      "rating_method": "sequential_elo",
      "raw_elo": 1555.7512446698092,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 43.39507194961651,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 217
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1050,
      "canonical_public_row_identity": "publication-row.v1:balanced:google-gemini-3-5-flash:099e26902a6430db",
      "capped_draws": 80,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 10
        },
        "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": 42.70271893536102,
      "contributing_entrants": null,
      "distinct_rated_opponents": 42,
      "draws": 323,
      "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": "2026-09-10T11:09:43Z",
      "losses": 407,
      "max_score": 69.56944867447089,
      "measured_at": null,
      "min_score": 12.10378519941586,
      "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": 1049,
      "rating_method": "sequential_elo",
      "raw_elo": 1544.1927472622533,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 42.70271893536102,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 319
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 572,
      "canonical_public_row_identity": "publication-row.v1:balanced:claude-opus-4-8:0b9e44df31643ae8",
      "capped_draws": 82,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "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": 42.12697825585987,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 228,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": "2026-08-05T03:49:27Z",
      "losses": 134,
      "max_score": 70.46838917607434,
      "measured_at": null,
      "min_score": 10.886852859373011,
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 572,
      "rating_method": "sequential_elo",
      "raw_elo": 1555.5846759385058,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 42.12697825585987,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 210
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 621,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-4-mini:b89689b888a03e98",
      "capped_draws": 40,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "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": 41.94270122706257,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 182,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": "2026-08-05T06:55:18Z",
      "losses": 182,
      "max_score": 56.015466910410275,
      "measured_at": null,
      "min_score": 15.520290105513986,
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 619,
      "rating_method": "sequential_elo",
      "raw_elo": 1533.158871524542,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 41.94270122706257,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 255
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 486,
      "canonical_public_row_identity": "publication-row.v1:balanced:qwen-qwen3-7-plus:d327d3640f27bd3b",
      "capped_draws": 91,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 16
        },
        "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": 0.43500896
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 44.42570551005691,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 150,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T03:48:47Z",
      "losses": 158,
      "max_score": 70.99957787144118,
      "measured_at": null,
      "min_score": 15.204208993992154,
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 486,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.324560555531,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 41.34277741669788,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 178
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1541,
      "canonical_public_row_identity": "publication-row.v1:balanced:meta-muse-spark-1-2:996fe7c6ac30c7b0",
      "capped_draws": 63,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "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": 0.37616799999999995
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.735701184984805,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 379,
      "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": "2026-09-10T10:59:40Z",
      "losses": 549,
      "max_score": 64.21230002498487,
      "measured_at": null,
      "min_score": 13.992136416293384,
      "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": 1540,
      "rating_method": "sequential_elo",
      "raw_elo": 1558.3591357051268,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 41.33261162389615,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 612
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1018,
      "canonical_public_row_identity": "publication-row.v1:balanced:deepseek-deepseek-v4-pro:768bc94990435e72",
      "capped_draws": 13,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "evidence_basis": "Provider-reported",
        "max": 0.06923239834,
        "mean": 0.046577516286750005,
        "median": 0.0458058365,
        "min": 0.023862969,
        "recorded_attempt_count": 12,
        "run_count": 8,
        "total": 0.372620130294
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.91602273478811,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 237,
      "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": "2026-09-10T10:50:08Z",
      "losses": 354,
      "max_score": 65.49910556920233,
      "measured_at": null,
      "min_score": 8.46888583743832,
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1018,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.129488075388,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 40.91602273478811,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 427
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 484,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5:2447de160165f34c",
      "capped_draws": 61,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "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": 42.256499987447725,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 138,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "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": "2026-08-05T05:19:06Z",
      "losses": 160,
      "max_score": 64.90905738242017,
      "measured_at": null,
      "min_score": 25.31798930091367,
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 484,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.3373874396289,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 40.869143459380226,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 186
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1136,
      "canonical_public_row_identity": "publication-row.v1:balanced:qwen-qwen3-8-max:2315ff339b0c18d0",
      "capped_draws": 92,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "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": 39.97699964131566,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 371,
      "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": "2026-09-10T11:05:43Z",
      "losses": 410,
      "max_score": 61.62273404542139,
      "measured_at": null,
      "min_score": 12.997248213621113,
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1135,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.3432547298382,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 39.97699964131566,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 354
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 566,
      "canonical_public_row_identity": "publication-row.v1:balanced:qwen-qwen3-7-max:1ec5e86937e80891",
      "capped_draws": 83,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "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": 0.7288237500000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.38266609921668,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 206,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T05:35:11Z",
      "losses": 170,
      "max_score": 71.61968219996771,
      "measured_at": null,
      "min_score": 12.895585775886488,
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 566,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.1180674247914,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 39.05683089161168,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 190
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1444,
      "canonical_public_row_identity": "publication-row.v1:balanced:z-ai-glm-5-2:ce87a33d1a10c901",
      "capped_draws": 273,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 26
        },
        "evidence_basis": "Provider-reported",
        "max": 0.14635563000000001,
        "mean": 0.0939111476625,
        "median": 0.10304704349999999,
        "min": 0.032703412,
        "recorded_attempt_count": 26,
        "run_count": 16,
        "total": 1.5025783626000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.64130225632867,
      "contributing_entrants": null,
      "distinct_rated_opponents": 62,
      "draws": 573,
      "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": "2026-09-10T11:10:18Z",
      "losses": 467,
      "max_score": 72.14085667254591,
      "measured_at": null,
      "min_score": 18.056375254178352,
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1444,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.5810263446235,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 38.64130225632867,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 404
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 492,
      "canonical_public_row_identity": "publication-row.v1:balanced:moonshotai-kimi-k2-7-code:bad3fe5c7b1e8a5f",
      "capped_draws": 10,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "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": 41.10005622496815,
      "contributing_entrants": null,
      "distinct_rated_opponents": 32,
      "draws": 143,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T05:26:41Z",
      "losses": 159,
      "max_score": 55.31987902290327,
      "measured_at": null,
      "min_score": 15.971215353629413,
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 492,
      "rating_method": "sequential_elo",
      "raw_elo": 1543.1361607461313,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 38.247912032324855,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 190
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2230,
      "canonical_public_row_identity": "publication-row.v1:balanced:moonshotai-kimi-k3:b25ef0843c2d972a",
      "capped_draws": 294,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 16
        },
        "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": 37.79492618629287,
      "contributing_entrants": null,
      "distinct_rated_opponents": 61,
      "draws": 758,
      "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": "2026-09-10T10:40:09Z",
      "losses": 792,
      "max_score": 60.02690569508898,
      "measured_at": null,
      "min_score": 6.485222218768579,
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2220,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.9366584163504,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 37.79492618629287,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1058,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-6-terra:0fc18f792ad6d67d",
      "capped_draws": 42,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "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": 37.628448345284106,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 301,
      "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": "2026-09-10T10:58:30Z",
      "losses": 443,
      "max_score": 61.83347349707339,
      "measured_at": null,
      "min_score": 10.442043596500689,
      "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": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1058,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.9798187871947,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 37.628448345284106,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 314
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 884,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-4-nano:65879fd5791a5546",
      "capped_draws": 63,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 25
        },
        "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": 0.39544915
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 39.62662596514345,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 172,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "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": "2026-08-05T06:55:07Z",
      "losses": 344,
      "max_score": 60.07944202124918,
      "measured_at": null,
      "min_score": 12.950917619586493,
      "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": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 882,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.6010568667577,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 36.87673067298392,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 366
    },
    {
      "admitted_plugins": 26,
      "attempted_matches": 3609,
      "canonical_public_row_identity": "publication-row.v1:balanced:stealth-ox-alpha:03024ebf053d776c",
      "capped_draws": 225,
      "codegen_cost_usd": {
        "admitted_cell_count": 26,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 39
        },
        "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": 36.85392471914304,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 847,
      "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": "2026-09-10T11:12:08Z",
      "losses": 1488,
      "max_score": 48.22093354536652,
      "measured_at": null,
      "min_score": 16.948694007756043,
      "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": 3600,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.2697748344724,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 35.55877308298843,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1265
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 620,
      "canonical_public_row_identity": "publication-row.v1:balanced:x-ai-grok-build-0-1:32469550859abedd",
      "capped_draws": 84,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "evidence_basis": "Provider-reported",
        "max": 0.07439860000000001,
        "mean": 0.060660574999999994,
        "median": 0.0565846,
        "min": 0.0485456,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 0.48528459999999995
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 35.20852304594772,
      "contributing_entrants": null,
      "distinct_rated_opponents": 32,
      "draws": 230,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T05:34:43Z",
      "losses": 205,
      "max_score": 65.57660382357807,
      "measured_at": null,
      "min_score": 12.336802440575292,
      "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": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 620,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.342191111961,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 35.20852304594772,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 185
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1154,
      "canonical_public_row_identity": "publication-row.v1:balanced:deepseek-deepseek-v4-pro-0813:e2a09b34905fa7a8",
      "capped_draws": 181,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "evidence_basis": "Provider-reported",
        "max": 0.18085216,
        "mean": 0.12355654023,
        "median": 0.14129957716,
        "min": 0.04648314,
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.9884523218400001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 34.223607878349945,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 348,
      "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": "2026-09-10T11:10:07Z",
      "losses": 435,
      "max_score": 71.89246349927906,
      "measured_at": null,
      "min_score": 0.0,
      "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": 1148,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.9387678678388,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 34.223607878349945,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 365
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1733,
      "canonical_public_row_identity": "publication-row.v1:balanced:claude-sonnet-5:765bc291b12a711e",
      "capped_draws": 228,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "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": 33.75922437630374,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 573,
      "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": "2026-09-10T11:08:22Z",
      "losses": 573,
      "max_score": 50.753970891959106,
      "measured_at": null,
      "min_score": 13.459089329828975,
      "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": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1733,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.7515433483236,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 33.75922437630374,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 587
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1134,
      "canonical_public_row_identity": "publication-row.v1:balanced:qwen-qwen3-8-2-4t-a95b:a41a9f6e42ee2b8f",
      "capped_draws": 166,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "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": 33.21730372205993,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 428,
      "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": "2026-09-10T10:48:35Z",
      "losses": 375,
      "max_score": 50.52600493863421,
      "measured_at": null,
      "min_score": 8.285036037313507,
      "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": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1131,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.2517713468794,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 33.21730372205993,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 328
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1725,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-6-luna:56b3e8082c8d4caf",
      "capped_draws": 196,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "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": 0.05054445
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 33.21050354010995,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 590,
      "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": "2026-09-10T11:05:04Z",
      "losses": 614,
      "max_score": 51.75536719315471,
      "measured_at": null,
      "min_score": 12.208818148161988,
      "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": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1724,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.187551087428,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 33.21050354010995,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 520
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 898,
      "canonical_public_row_identity": "publication-row.v1:balanced:bytedance-seed-seed-2-0-code:4f756096d2af64d1",
      "capped_draws": 32,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "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": 0.42810400000000004
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 32.72437884008807,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 245,
      "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": "2026-09-10T10:09:47Z",
      "losses": 334,
      "max_score": 74.84224837474918,
      "measured_at": null,
      "min_score": 5.142930493219368,
      "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": 898,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.8884134687767,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 31.649978910509514,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 319
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1898,
      "canonical_public_row_identity": "publication-row.v1:balanced:deepseek-deepseek-v4-flash:23183d74d990acfd",
      "capped_draws": 192,
      "codegen_cost_usd": {
        "admitted_cell_count": 22,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 36
        },
        "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": 32.48806112461729,
      "contributing_entrants": null,
      "distinct_rated_opponents": 63,
      "draws": 626,
      "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": "2026-09-10T11:08:34Z",
      "losses": 720,
      "max_score": 41.99995218852661,
      "measured_at": null,
      "min_score": 10.294264101835623,
      "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": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1896,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.329183315615,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 31.42141992861472,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 550
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1150,
      "canonical_public_row_identity": "publication-row.v1:balanced:xiaomi-mimo-v2-5:9e3a1125fb872e8c",
      "capped_draws": 87,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 52
        },
        "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": 0.48618750699999996
      },
      "codegen_evaluated_cells": 12,
      "conditional_success_score": 32.790258691009186,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 422,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T04:57:10Z",
      "losses": 418,
      "max_score": 45.99727906392186,
      "measured_at": null,
      "min_score": 15.194114602701864,
      "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": 40,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1150,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.7594960134609,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 29.629343452081027,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 310
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 512,
      "canonical_public_row_identity": "publication-row.v1:balanced:google-gemini-3-1-flash-lite:a27c54e25bfb4de0",
      "capped_draws": 71,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "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": 0.08108399999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 31.22469222252498,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 128,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "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": "2026-08-05T05:18:42Z",
      "losses": 245,
      "max_score": 42.02538255150319,
      "measured_at": null,
      "min_score": 13.765200753063453,
      "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": 41,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 510,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.138297710363,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 29.057850306249282,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 137
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 364,
      "canonical_public_row_identity": "publication-row.v1:balanced:nvidia-nemotron-3-ultra-550b-a55b:3bcb1a7b4e915226",
      "capped_draws": 68,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 21
        },
        "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": 33.17879341527922,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 135,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "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": "2026-08-05T03:41:43Z",
      "losses": 127,
      "max_score": 58.942903698869344,
      "measured_at": null,
      "min_score": 10.53671511272001,
      "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": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 364,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.7703846459403,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 28.644580216192928,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 102
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 576,
      "canonical_public_row_identity": "publication-row.v1:balanced:minimax-minimax-m3:31a675d7727a5125",
      "capped_draws": 78,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "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": 27.094189624924688,
      "contributing_entrants": null,
      "distinct_rated_opponents": 32,
      "draws": 191,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T04:04:06Z",
      "losses": 262,
      "max_score": 48.5556009285104,
      "measured_at": null,
      "min_score": 5.046768034226976,
      "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": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 576,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.5000954323484,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 26.204638884565124,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 123
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 368,
      "canonical_public_row_identity": "publication-row.v1:balanced:nex-agi-nex-n2-pro:ef6c9f2b08b0d606",
      "capped_draws": 14,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "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": 28.879374910115267,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 43,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T05:35:20Z",
      "losses": 223,
      "max_score": 47.74072823827207,
      "measured_at": null,
      "min_score": 7.328898964258992,
      "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": 44,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 368,
      "rating_method": "sequential_elo",
      "raw_elo": 1323.9636857229561,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 25.677798888726322,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 102
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 3264,
      "canonical_public_row_identity": "publication-row.v1:balanced:meituan-longcat-2-0:26225fa06d2cccd9",
      "capped_draws": 231,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 70
        },
        "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": 27.242268163777958,
      "contributing_entrants": null,
      "distinct_rated_opponents": 60,
      "draws": 862,
      "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": "2026-09-10T10:39:01Z",
      "losses": 1567,
      "max_score": 42.612280911763705,
      "measured_at": null,
      "min_score": 5.565460776989309,
      "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": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3230,
      "rating_method": "sequential_elo",
      "raw_elo": 1371.1939426278043,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 25.351787126174198,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 33,
      "wins": 801
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 990,
      "canonical_public_row_identity": "publication-row.v1:balanced:openai-gpt-oss-120b:8fc70fdaca40b3e0",
      "capped_draws": 162,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "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": 24.648172544378482,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 400,
      "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": "2026-09-10T10:52:53Z",
      "losses": 376,
      "max_score": 38.95744773414053,
      "measured_at": null,
      "min_score": 9.805861440635663,
      "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": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 990,
      "rating_method": "sequential_elo",
      "raw_elo": 1330.7221983901602,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 24.648172544378482,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 214
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": 2985,
      "canonical_public_row_identity": "publication-row.v1:balanced:poolside-laguna-s-2-1:df6bf1faab8cda70",
      "capped_draws": 498,
      "codegen_cost_usd": {
        "admitted_cell_count": 11,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 35
        },
        "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": 24.290531112031516,
      "contributing_entrants": null,
      "distinct_rated_opponents": 61,
      "draws": 1302,
      "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": "2026-09-10T10:57:42Z",
      "losses": 1119,
      "max_score": 40.16991479649198,
      "measured_at": null,
      "min_score": 11.01099847514966,
      "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": 47,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2985,
      "rating_method": "sequential_elo",
      "raw_elo": 1342.6238101954334,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 22.86931587697147,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 564
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 958,
      "canonical_public_row_identity": "publication-row.v1:balanced:meta-muse-glimmer-30b:05ba243db4d890c1",
      "capped_draws": 161,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "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": 22.81328793344419,
      "contributing_entrants": null,
      "distinct_rated_opponents": 42,
      "draws": 407,
      "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": "2026-09-10T10:55:16Z",
      "losses": 346,
      "max_score": 39.83813064889331,
      "measured_at": null,
      "min_score": 8.950914647096557,
      "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": 48,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 958,
      "rating_method": "sequential_elo",
      "raw_elo": 1310.9758552377175,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 22.81328793344419,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 205
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 3581,
      "canonical_public_row_identity": "publication-row.v1:balanced:google-gemini-3-5-flash-lite:ada8852a63812f17",
      "capped_draws": 593,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 48
        },
        "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": 23.147895521816984,
      "contributing_entrants": null,
      "distinct_rated_opponents": 61,
      "draws": 1277,
      "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": "2026-09-10T11:06:31Z",
      "losses": 1589,
      "max_score": 39.89414504066892,
      "measured_at": null,
      "min_score": 11.967580414073916,
      "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": 49,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3571,
      "rating_method": "sequential_elo",
      "raw_elo": 1300.4728466012357,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 22.38790868020074,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 705
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1198,
      "canonical_public_row_identity": "publication-row.v1:balanced:thinkingmachines-inkling-small:76482ff3d2fed50c",
      "capped_draws": 135,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "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": 21.132069816135214,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 409,
      "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": "2026-09-10T10:54:12Z",
      "losses": 543,
      "max_score": 54.086740109183,
      "measured_at": null,
      "min_score": 0.0,
      "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": 50,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1198,
      "rating_method": "sequential_elo",
      "raw_elo": 1286.4616974117926,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 20.518892029756675,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 246
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 722,
      "canonical_public_row_identity": "publication-row.v1:balanced:inception-mercury-2-5-preview:6204f9f816b5cf60",
      "capped_draws": 117,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "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": 0.01012224
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 19.044072383738698,
      "contributing_entrants": null,
      "distinct_rated_opponents": 41,
      "draws": 315,
      "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": "2026-09-10T10:39:00Z",
      "losses": 306,
      "max_score": 30.71080462121027,
      "measured_at": null,
      "min_score": 6.865539546300709,
      "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": 51,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 721,
      "rating_method": "sequential_elo",
      "raw_elo": 1275.7209898590386,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 17.722506297399335,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 100
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2170,
      "canonical_public_row_identity": "publication-row.v1:balanced:claude-opus-4-5:6145092901d96725",
      "capped_draws": 116,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 16
        },
        "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": 42.43578753789422,
      "contributing_entrants": null,
      "distinct_rated_opponents": 63,
      "draws": 517,
      "eligibility_flag": false,
      "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": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-10T11:09:47Z",
      "losses": 753,
      "max_score": 59.105299689263475,
      "measured_at": null,
      "min_score": 9.845278217768804,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 2168,
      "rating_method": "sequential_elo",
      "raw_elo": 1528.1701319696285,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 42.43578753789422,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 898
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 398,
      "canonical_public_row_identity": "publication-row.v1:balanced:xiaomi-mimo-v2-5-pro:43c3a8c0c343b927",
      "capped_draws": 54,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "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": 44.10609034219564,
      "contributing_entrants": null,
      "distinct_rated_opponents": 32,
      "draws": 92,
      "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-v2.5-pro",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:11:01Z",
      "losses": 152,
      "max_score": 70.02330483752023,
      "measured_at": null,
      "min_score": 27.56700348772194,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 398,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.351739327467,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 41.04534198844345,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 154
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 334,
      "canonical_public_row_identity": "publication-row.v1:balanced:google-gemma-4-31b-it:dee0b5fdcae9fd5f",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 7,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "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": 42.37685841855066,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 55,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T03:57:18Z",
      "losses": 143,
      "max_score": 57.095657519959566,
      "measured_at": null,
      "min_score": 27.208177713775562,
      "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": 332,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.5393162508012,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 36.84420968400358,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 134
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 693,
      "canonical_public_row_identity": "publication-row.v1:balanced:qwen-qwen3-8-27b:395c64922f7fe00a",
      "capped_draws": 78,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "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": 34.62654964999745,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 120,
      "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": "2026-09-10T11:11:56Z",
      "losses": 322,
      "max_score": 50.69846903136761,
      "measured_at": null,
      "min_score": 18.985013985665347,
      "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": 692,
      "rating_method": "sequential_elo",
      "raw_elo": 1362.3511931585113,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 31.832973643106108,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 250
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:balanced:cohere-north-mini-code:568529666a0f96d5",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "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": 33.971196577578915,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 147,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T05:19:01Z",
      "losses": 190,
      "max_score": 49.11080098947388,
      "measured_at": null,
      "min_score": 22.98682614510266,
      "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": 486,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.5536195326868,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 31.613760604607553,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 149
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 320,
      "canonical_public_row_identity": "publication-row.v1:balanced:stepfun-step-3-7-flash:bf3021406df8f368",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "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": 0.31476170000000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 31.49301590711204,
      "contributing_entrants": null,
      "distinct_rated_opponents": 31,
      "draws": 120,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "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": "2026-08-05T05:11:10Z",
      "losses": 120,
      "max_score": 49.98510602874532,
      "measured_at": null,
      "min_score": 15.266282350907517,
      "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": 320,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.6971779128244,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 26.48236418181872,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1367,
      "canonical_public_row_identity": "publication-row.v1:balanced:thinkingmachines-inkling:3ab0a3aec8e194a6",
      "capped_draws": 268,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 53
        },
        "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": 26.69039305708575,
      "contributing_entrants": null,
      "distinct_rated_opponents": 63,
      "draws": 495,
      "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": "2026-09-10T10:39:04Z",
      "losses": 588,
      "max_score": 43.70587386646689,
      "measured_at": null,
      "min_score": 15.613204983285852,
      "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": 1364,
      "rating_method": "sequential_elo",
      "raw_elo": 1322.6602659949974,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 20.886361304870018,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 281
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:balanced:inclusionai-ling-3-0-flash:0cd16c129bab6df2",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 52
        },
        "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": 23.90120559075741,
      "contributing_entrants": null,
      "distinct_rated_opponents": 61,
      "draws": 467,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-09-10T10:27:32Z",
      "losses": 783,
      "max_score": 43.412761651647685,
      "measured_at": null,
      "min_score": 6.242872745526706,
      "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": 1620,
      "rating_method": "sequential_elo",
      "raw_elo": 1364.6961632417467,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 19.00792918857275,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 370
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-row.v1:balanced:ibm-granite-granite-4-2-8b:9c9c55a34daec5ca",
      "capped_draws": 105,
      "codegen_cost_usd": {
        "admitted_cell_count": 2,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "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": 10.934934183457305,
      "contributing_entrants": null,
      "distinct_rated_opponents": 38,
      "draws": 105,
      "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": "2026-09-10T11:06:08Z",
      "losses": 137,
      "max_score": 21.86986836691461,
      "measured_at": null,
      "min_score": 0.0,
      "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": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1109.390743883938,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 7.732166112951243,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 202,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-4:91029345b4b373cd",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "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-5.4",
        "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": "2026-09-10T10:25:37Z",
      "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": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 2181.186817301249,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:x-ai-grok-4-5:9ade9c53df23b855",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 7,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-08-03T18:34:47Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1796.9255894755222,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 66.95829181437593,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 2,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 198,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:meta-muse-spark-1-2:996fe7c6ac30c7b0",
      "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": "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": 45,
      "max_score": null,
      "measured_at": "2026-09-10T09:56:02Z",
      "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": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1746.306694043386,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 64.21230002498487,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 118,
      "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": 59,
      "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": 43,
      "max_score": null,
      "measured_at": "2026-09-10T10:00:26Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1725.6940221336674,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 61.83347349707339,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 204,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-6-sol:60281ce94ea88014",
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "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": "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": 77,
      "max_score": null,
      "measured_at": "2026-09-10T11:07:47Z",
      "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": 204,
      "rating_method": "sequential_elo",
      "raw_elo": 1712.4066257257862,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 61.45873236257106,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 154,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:claude-opus-5:f836f90d8fb9ff19",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 77,
      "draws": 15,
      "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": 37,
      "max_score": null,
      "measured_at": "2026-08-05T05:10:23Z",
      "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": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1729.9610845756647,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 61.43562510044728,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.465804565350075,
      "unilateral_faults": 0,
      "wins": 102
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 121,
      "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": 60,
      "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": 54,
      "max_score": null,
      "measured_at": "2026-09-10T11:12:08Z",
      "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": 119,
      "rating_method": "sequential_elo",
      "raw_elo": 1679.7741147045783,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 58.069604157521695,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.8935464587638418,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 356,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:google-gemini-3-6-flash:157bc5e3bd81a2f8",
      "capped_draws": 187,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 139,
      "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": "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": 48,
      "max_score": null,
      "measured_at": "2026-09-10T04:50:55Z",
      "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": 356,
      "rating_method": "sequential_elo",
      "raw_elo": 1676.8379285851024,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 57.908198892761675,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.79454145484633,
      "unilateral_faults": 0,
      "wins": 121
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 259,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:moonshotai-kimi-k3:b25ef0843c2d972a",
      "capped_draws": 43,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 92,
      "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": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-09-10T01:06:50Z",
      "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": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1661.6676787014649,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 57.5234825792159,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 119,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-6-astra:dd3177afdee2bb2a",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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-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": 44,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:15Z",
      "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": 119,
      "rating_method": "sequential_elo",
      "raw_elo": 1671.1890753713847,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 57.36356914969686,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.8935464587638418,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:google-gemini-3-5-flash:099e26902a6430db",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": "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": 56,
      "max_score": null,
      "measured_at": "2026-09-10T11:08:39Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1665.395177936089,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 56.899512876213336,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:google-gemini-3-8-flash:9fd2f22238c82925",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": "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": 49,
      "max_score": null,
      "measured_at": "2026-09-10T11:10:07Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1661.8397195918333,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 56.60711141333341,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-5:fc52395a742e5644",
      "capped_draws": 52,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 52,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:23:55Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1653.6326315257897,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.17385603478494,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-4-mini:b89689b888a03e98",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "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-5.4-mini",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T16:16:35Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1642.0222732482737,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.00765200217118,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 2,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:x-ai-grok-4-6:69246fd982959de2",
      "capped_draws": 33,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "draws": 33,
      "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": 59,
      "max_score": null,
      "measured_at": "2026-09-10T11:09:42Z",
      "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": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1621.1494007222223,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.57424063188693,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 120,
      "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": 60,
      "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": 57,
      "max_score": null,
      "measured_at": "2026-09-10T11:10:23Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1621.4320540516248,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.28397853663737,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:claude-fable-5:4fee988c3b8ad119",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 15,
      "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": 54,
      "max_score": null,
      "measured_at": "2026-09-10T11:07:59Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1601.767086979764,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 51.666728499497296,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:z-ai-glm-5-3-flash:1cd9221832b4ca47",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": "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": 58,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:10Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1596.763908226237,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 51.25526627861526,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:qwen-qwen3-8-2-4t-a95b:a41a9f6e42ee2b8f",
      "capped_draws": 41,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 41,
      "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": 61,
      "max_score": null,
      "measured_at": "2026-09-10T01:49:09Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1585.9593303575618,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.52600493863421,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 298,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:claude-opus-4-5:6145092901d96725",
      "capped_draws": 84,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 84,
      "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": 99,
      "max_score": null,
      "measured_at": "2026-09-10T11:09:47Z",
      "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": 298,
      "rating_method": "sequential_elo",
      "raw_elo": 1562.931340214569,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.56099324474412,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 115
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:stealth-ox-alpha:03024ebf053d776c",
      "capped_draws": 64,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 142,
      "draws": 64,
      "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": 114,
      "max_score": null,
      "measured_at": "2026-09-10T11:12:08Z",
      "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": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 1557.5471242852395,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.22093354536652,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.8522727272727293,
      "unilateral_faults": 0,
      "wins": 100
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 146,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:tencent-hy4-preview:a81918b0d5baba2a",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "draws": 10,
      "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": 86,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:19Z",
      "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": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.6533895280302,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.013416130569944,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:deepseek-deepseek-v4-pro:768bc94990435e72",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "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-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": 83,
      "max_score": null,
      "measured_at": "2026-09-10T09:51:03Z",
      "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": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.056868577737,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.836055739473956,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 174,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:z-ai-glm-5-3:ebf51d85881ca5b8",
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 87,
      "draws": 26,
      "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": 81,
      "max_score": null,
      "measured_at": "2026-09-10T11:09:42Z",
      "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": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.5022233610664,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.58269393252839,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:o3:9e4cf63e80682b9b",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "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": "o3",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:22:08Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.7878014821274,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.26017199969047,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:moonshotai-kimi-k2-7-code:bad3fe5c7b1e8a5f",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "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": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T01:23:03Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1515.2417696657326,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.01459558203363,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:x-ai-grok-build-0-1:32469550859abedd",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 17,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 27,
      "max_score": null,
      "measured_at": "2026-08-04T20:42:26Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.378396323981,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.119446315546206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:claude-opus-4-8:0b9e44df31643ae8",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 15,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:21:46Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.3231224366134,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.09168274262431,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 165,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:qwen-qwen3-8-flash:5a72b22afc48c9d2",
      "capped_draws": 65,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 83,
      "draws": 65,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:42Z",
      "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": 165,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.517249176712,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.79036526143108,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:qwen-qwen3-7-plus:d327d3640f27bd3b",
      "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": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 32,
      "max_score": null,
      "measured_at": "2026-08-03T09:57:34Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.5386153907175,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.34815521713447,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:google-gemini-3-1-flash-lite:a27c54e25bfb4de0",
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "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": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:21:14Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.886972534093,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.80592199500637,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:nvidia-nemotron-3-ultra-550b-a55b:3bcb1a7b4e915226",
      "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": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T02:39:09Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.0591958988462,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.78469219527432,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 168,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:deepseek-deepseek-v4-pro-0813:e2a09b34905fa7a8",
      "capped_draws": 117,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "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": "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": 18,
      "max_score": null,
      "measured_at": "2026-09-10T11:10:07Z",
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.6924784481903,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.51169686092654,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 241,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-6-luna:56b3e8082c8d4caf",
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 92,
      "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": "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": 93,
      "max_score": null,
      "measured_at": "2026-09-10T11:05:04Z",
      "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": 241,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.15171118097,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.4718506514852,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 282,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:poolside-laguna-s-2-1:df6bf1faab8cda70",
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "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": "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": 116,
      "max_score": null,
      "measured_at": "2026-09-10T09:58:35Z",
      "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": 282,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.3853679490633,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 40.16991479649198,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 616,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:google-gemini-3-5-flash-lite:ada8852a63812f17",
      "capped_draws": 120,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 220,
      "draws": 120,
      "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": 237,
      "max_score": null,
      "measured_at": "2026-09-10T09:53:51Z",
      "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": 616,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.1140497986676,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.89414504066892,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 259
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:openai-gpt-oss-120b:8fc70fdaca40b3e0",
      "capped_draws": 34,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 68,
      "draws": 34,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-09-10T06:22:35Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.0391376524533,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 38.95744773414053,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 3,
      "attempted_matches": 276,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:deepseek-deepseek-v4-flash:23183d74d990acfd",
      "capped_draws": 31,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 137,
      "draws": 31,
      "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": 144,
      "max_score": null,
      "measured_at": "2026-09-10T07:19:38Z",
      "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": 274,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.3815698323801,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 38.30464422301185,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.730662565860658,
      "unilateral_faults": 0,
      "wins": 99
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 221,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:claude-sonnet-5:765bc291b12a711e",
      "capped_draws": 50,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "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-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": 74,
      "max_score": null,
      "measured_at": "2026-09-10T05:36:36Z",
      "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": 221,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.215755307793,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 38.09431108312192,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:qwen-qwen3-8-max:2315ff339b0c18d0",
      "capped_draws": 62,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "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": "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": 34,
      "max_score": null,
      "measured_at": "2026-09-10T11:05:43Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.6091705822635,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.585502632645984,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 212,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:z-ai-glm-5-2:ce87a33d1a10c901",
      "capped_draws": 110,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 106,
      "draws": 110,
      "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": 42,
      "max_score": null,
      "measured_at": "2026-09-10T03:17:54Z",
      "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": 212,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.1271705787317,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.27778068209783,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.2214632714423,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 152,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:bytedance-seed-seed-2-0-code:4f756096d2af64d1",
      "capped_draws": 28,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 76,
      "draws": 28,
      "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": 56,
      "max_score": null,
      "measured_at": "2026-09-10T09:45:46Z",
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.2377140826875,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.15102612381427,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 166,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:xiaomi-mimo-v2-5:9e3a1125fb872e8c",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 77,
      "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-v2.5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 81,
      "max_score": null,
      "measured_at": "2026-08-05T01:23:13Z",
      "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": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1390.5996054009402,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.69985907503834,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.830591148722647,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:minimax-minimax-m3:31a675d7727a5125",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "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": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 49,
      "max_score": null,
      "measured_at": "2026-08-05T02:21:31Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1350.9691174196694,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.37649642208813,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:thinkingmachines-inkling:3ab0a3aec8e194a6",
      "capped_draws": 76,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 90,
      "draws": 76,
      "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": 120,
      "max_score": null,
      "measured_at": "2026-09-10T09:56:33Z",
      "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": 1301.8495200374323,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.89888466985854,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:meta-muse-glimmer-30b:05ba243db4d890c1",
      "capped_draws": 48,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 48,
      "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": 54,
      "max_score": null,
      "measured_at": "2026-09-10T09:57:21Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1303.0183569125913,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.097585157882463,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5:2447de160165f34c",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "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-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:11:21Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1292.4869742782632,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.31798930091367,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 121,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:qwen-qwen3-8-27b:395c64922f7fe00a",
      "capped_draws": 74,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 74,
      "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": 30,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:56Z",
      "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": 121,
      "rating_method": "sequential_elo",
      "raw_elo": 1280.5318378187312,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.260571807798776,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.5178730212592662,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "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:0cd16c129bab6df2",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 14,
      "draws": 70,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 167,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:55Z",
      "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": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1277.318453124216,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.818807678882663,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:qwen-qwen3-7-max:1ec5e86937e80891",
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 24,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 38,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:20Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1267.5817664088527,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.323632491834545,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 144,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-4-nano:65879fd5791a5546",
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 69,
      "draws": 26,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:22:02Z",
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1258.698860860387,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.50128480022854,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.166122297570965,
      "unilateral_faults": 2,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:thinkingmachines-inkling-small:76482ff3d2fed50c",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": "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": 114,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:00Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 971.3356846908011,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 104,
      "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": 52,
      "draws": 14,
      "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": 7,
      "max_score": null,
      "measured_at": "2026-09-10T10:09:03Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1834.7977187233885,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 79.6736533842389,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 83
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 36,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:00Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1782.338822767404,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 70.22687532833427,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 60
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 100,
      "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": 50,
      "draws": 38,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-03T12:23:36Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1661.2356908966067,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.36178169780819,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 26.264004201400486,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 168,
      "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": 70,
      "draws": 94,
      "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": 18,
      "max_score": null,
      "measured_at": "2026-09-10T09:57:15Z",
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1600.6853646986274,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.00346679320183,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 104,
      "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": 52,
      "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": "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": 18,
      "max_score": null,
      "measured_at": "2026-09-10T09:54:19Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1569.6854300230325,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.93233314474059,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:gpt-5-5:fc52395a742e5644",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 24,
      "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-5.5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T09:39:04Z",
      "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": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1580.7065130209066,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.656330153885765,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 27.678571428571434,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 61,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-09-10T09:53:31Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.1931602057512,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.901057918937127,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 71,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-09-10T09:49:55Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.8916581476587,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.766285822102056,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 58,
      "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": 29,
      "max_score": null,
      "measured_at": "2026-09-10T09:50:33Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.8092095628847,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 21.32992572991054,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "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": "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": 21,
      "max_score": null,
      "measured_at": "2026-09-10T09:49:12Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.3429910044993,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 18.364695347029407,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 16
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 150,
      "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": 75,
      "draws": 112,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-09-10T09:51:01Z",
      "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": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.2858557746495,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 18.056375254178352,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 17.11374969818697,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 372,
      "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": 186,
      "draws": 280,
      "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": 55,
      "max_score": null,
      "measured_at": "2026-09-10T09:53:16Z",
      "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": 372,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.8477800060446,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 16.948694007756043,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.3633357649511098,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:moonshotai-kimi-k2-7-code:bad3fe5c7b1e8a5f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 75,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 12,
      "max_score": null,
      "measured_at": "2026-08-03T14:15:10Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.9471496450988,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 15.971215353629413,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:gpt-5-4-mini:b89689b888a03e98",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 66,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:16:41Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.9829898555085,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 15.520290105513986,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 215,
      "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": 85,
      "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": "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": 40,
      "max_score": null,
      "measured_at": "2026-09-10T07:39:30Z",
      "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": 215,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.9244064409238,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 15.37552954010579,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:stepfun-step-3-7-flash:bf3021406df8f368",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 58,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T09:30:46Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.71508709671,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 15.266282350907517,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:qwen-qwen3-7-plus:d327d3640f27bd3b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 59,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 2,
      "max_score": null,
      "measured_at": "2026-08-03T14:15:15Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.1517568183824,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 15.204208993992154,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 188,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:xiaomi-mimo-v2-5:9e3a1125fb872e8c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 87,
      "draws": 169,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-03T04:42:24Z",
      "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": 1487.7432210455304,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 15.194114602701864,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 18.803478064443254,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "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": 36,
      "draws": 52,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-08-02T23:10:13Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.9101853302607,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 15.084858110615464,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "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": 99,
      "draws": 230,
      "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": 26,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:45Z",
      "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": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.9009704052921,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 13.63565896036477,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 146,
      "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": 73,
      "draws": 105,
      "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": 32,
      "max_score": null,
      "measured_at": "2026-09-10T09:49:06Z",
      "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": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.001763083591,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 13.629201190774216,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 176,
      "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": 71,
      "draws": 164,
      "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": 6,
      "max_score": null,
      "measured_at": "2026-09-10T07:14:14Z",
      "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": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.1315122058427,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 13.459089329828975,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 152,
      "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": 70,
      "draws": 122,
      "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": 28,
      "max_score": null,
      "measured_at": "2026-09-10T07:14:17Z",
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.8391048767317,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.997248213621113,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:gpt-5-4-nano:65879fd5791a5546",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 59,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:15:35Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.4584951256152,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.950917619586493,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:qwen-qwen3-7-max:1ec5e86937e80891",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 61,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 6,
      "max_score": null,
      "measured_at": "2026-08-03T03:19:01Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.4077462615205,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.895585775886488,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": "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": 31,
      "max_score": null,
      "measured_at": "2026-09-10T07:15:09Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.2230129143188,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.807246879163486,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:x-ai-grok-build-0-1:32469550859abedd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 62,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 1,
      "max_score": null,
      "measured_at": "2026-08-03T12:16:24Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.4473944599374,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.336802440575292,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 182,
      "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": 67,
      "draws": 171,
      "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": 6,
      "max_score": null,
      "measured_at": "2026-09-10T09:49:03Z",
      "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": 182,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.6916419866793,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.208818148161988,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 160,
      "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": 80,
      "draws": 131,
      "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": 28,
      "max_score": null,
      "measured_at": "2026-09-10T07:15:16Z",
      "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": 1452.0639490111673,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.10378519941586,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 492,
      "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": 174,
      "draws": 446,
      "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": 45,
      "max_score": null,
      "measured_at": "2026-09-10T06:13:02Z",
      "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": 492,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.952322485975,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.080494482193536,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 219,
      "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": 74,
      "draws": 215,
      "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": 4,
      "max_score": null,
      "measured_at": "2026-09-10T09:49:09Z",
      "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": 219,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.7511685714164,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 11.967580414073916,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 183,
      "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": 68,
      "draws": 157,
      "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": 18,
      "max_score": null,
      "measured_at": "2026-09-10T06:13:05Z",
      "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": 183,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.1968175126713,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 11.95411986023037,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:claude-opus-4-8:0b9e44df31643ae8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 54,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T05:47:14Z",
      "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": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.8573511124794,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.886852859373011,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:nvidia-nemotron-3-ultra-550b-a55b:3bcb1a7b4e915226",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "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": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T04:41:42Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.451330904213,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.53671511272001,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "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": 53,
      "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": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-09-10T10:03:45Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.9811763064577,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.442043596500689,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 5
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 224,
      "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": 112,
      "draws": 210,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-09-10T09:45:47Z",
      "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": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.006280236537,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.294264101835623,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 14.591247874473638,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 226,
      "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": 80,
      "draws": 210,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-09-10T07:13:02Z",
      "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": 1434.5467518430132,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 9.845278217768804,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 104,
      "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": 52,
      "draws": 102,
      "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": 2,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:35Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.814937022176,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 9.805861440635663,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "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": 53,
      "draws": 101,
      "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": 4,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:35Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.700789284466,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 8.950914647096557,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 96,
      "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": 6,
      "max_score": null,
      "measured_at": "2026-09-10T09:45:47Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.390578828434,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 8.46888583743832,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "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": 55,
      "draws": 113,
      "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": 3,
      "max_score": null,
      "measured_at": "2026-09-10T09:44:42Z",
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.1998400127345,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 8.444620292408556,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "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": 55,
      "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": "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": 26,
      "max_score": null,
      "measured_at": "2026-09-10T07:14:27Z",
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.930131541753,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 8.038357928704011,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 93,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:52Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.2471822852578,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 7.902824182042486,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "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": "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": 4,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:47Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.4870377723773,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 6.865539546300709,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 200,
      "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": 68,
      "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": "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": 27,
      "max_score": null,
      "measured_at": "2026-09-10T09:49:03Z",
      "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": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.5529196297932,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 6.485222218768579,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 74,
      "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": 37,
      "draws": 68,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-08-03T14:15:10Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.3417075004436,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 6.451833831046862,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:minimax-minimax-m3:31a675d7727a5125",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 54,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 8,
      "max_score": null,
      "measured_at": "2026-08-03T08:16:45Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.5933872534667,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 6.27975662875229,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "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:0cd16c129bab6df2",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 8,
      "draws": 191,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 27,
      "max_score": null,
      "measured_at": "2026-09-10T09:44:50Z",
      "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": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.4013902664049,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 6.242872745526706,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 104,
      "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": 52,
      "draws": 90,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-09-10T09:49:00Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.9212187647054,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 5.142930493219368,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "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": 66,
      "draws": 12,
      "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": 14,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:16Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1950.600091461118,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 85.0569619016003,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "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": 66,
      "draws": 46,
      "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": 6,
      "max_score": null,
      "measured_at": "2026-09-10T10:59:10Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1849.1528943906224,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 74.50207337964267,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "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": 66,
      "draws": 35,
      "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": 14,
      "max_score": null,
      "measured_at": "2026-09-10T11:00:17Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1816.03943786734,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 71.05684421340891,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 114,
      "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": 57,
      "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",
        "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": 12,
      "max_score": null,
      "measured_at": "2026-08-05T04:20:59Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1802.657390906043,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 67.80798395215069,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 21.910536671832062,
      "unilateral_faults": 0,
      "wins": 98
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "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": 66,
      "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": "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": 39,
      "max_score": null,
      "measured_at": "2026-09-10T10:57:29Z",
      "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": 131,
      "rating_method": "sequential_elo",
      "raw_elo": 1677.0077846493843,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 56.577906094603094,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:qwen-qwen3-8-flash:5a72b22afc48c9d2",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 32,
      "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": 40,
      "max_score": null,
      "measured_at": "2026-09-10T10:58:11Z",
      "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": 131,
      "rating_method": "sequential_elo",
      "raw_elo": 1674.4366977746672,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 56.31040205184428,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 138,
      "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": 66,
      "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": "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": 39,
      "max_score": null,
      "measured_at": "2026-09-10T11:00:55Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1657.7631805155133,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.5892798029273,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 210,
      "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": 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-5.6-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": 75,
      "max_score": null,
      "measured_at": "2026-09-10T11:01:12Z",
      "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": 209,
      "rating_method": "sequential_elo",
      "raw_elo": 1649.65448556946,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.48243593724166,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 109
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "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": 66,
      "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": "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": 35,
      "max_score": null,
      "measured_at": "2026-09-10T11:00:08Z",
      "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": 131,
      "rating_method": "sequential_elo",
      "raw_elo": 1616.442752927784,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.27652787410777,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:google-gemini-3-5-flash:099e26902a6430db",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 35,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-09-10T11:00:21Z",
      "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": 131,
      "rating_method": "sequential_elo",
      "raw_elo": 1586.9153526524012,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.204403387185614,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:thinkingmachines-inkling:3ab0a3aec8e194a6",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 90,
      "draws": 51,
      "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": 80,
      "max_score": null,
      "measured_at": "2026-09-10T04:29:56Z",
      "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": 247,
      "rating_method": "sequential_elo",
      "raw_elo": 1543.8740996061813,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.70587386646689,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:moonshotai-kimi-k3:b25ef0843c2d972a",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 90,
      "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": "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": 64,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:09Z",
      "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": 241,
      "rating_method": "sequential_elo",
      "raw_elo": 1532.8658749771148,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.5279830685233,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 7,
      "attempted_matches": 1051,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:stealth-ox-alpha:03024ebf053d776c",
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 7,
      "distinct_rated_opponents": 522,
      "draws": 206,
      "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": 412,
      "max_score": null,
      "measured_at": "2026-09-10T11:01:27Z",
      "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": 1042,
      "rating_method": "sequential_elo",
      "raw_elo": 1538.0029662977238,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.32178294840338,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 424
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 140,
      "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": 67,
      "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": "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": 54,
      "max_score": null,
      "measured_at": "2026-09-10T07:36:12Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.6857905884385,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.018834351295574,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 144,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:qwen-qwen3-8-max:2315ff339b0c18d0",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 71,
      "draws": 48,
      "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": 56,
      "max_score": null,
      "measured_at": "2026-09-10T10:47:44Z",
      "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": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.1049810468219,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.5639073510403,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 292,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:claude-opus-4-5:6145092901d96725",
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 130,
      "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": 95,
      "max_score": null,
      "measured_at": "2026-09-10T07:01:33Z",
      "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": 291,
      "rating_method": "sequential_elo",
      "raw_elo": 1521.0234426696943,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.5356517346492,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 162,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:bytedance-seed-seed-2-0-code:4f756096d2af64d1",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 41,
      "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": 84,
      "max_score": null,
      "measured_at": "2026-09-10T08:14:45Z",
      "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": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1525.3993880554747,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.16668933391658,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:meta-muse-spark-1-2:996fe7c6ac30c7b0",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 99,
      "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": "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": 97,
      "max_score": null,
      "measured_at": "2026-09-10T10:59:40Z",
      "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": 249,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.8099657675816,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.96423888645114,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 186,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:qwen-qwen3-8-2-4t-a95b:a41a9f6e42ee2b8f",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 92,
      "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/qwen3.8-2.4t-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": 67,
      "max_score": null,
      "measured_at": "2026-09-10T10:48:35Z",
      "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": 183,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.1251507851525,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 36.7519074126838,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 56,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:x-ai-grok-4-5:9ade9c53df23b855",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "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": "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": 20,
      "max_score": null,
      "measured_at": "2026-08-05T05:42:30Z",
      "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": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.227845346718,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 36.50322253143216,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 61,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5-4-mini:b89689b888a03e98",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 33,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T06:55:18Z",
      "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": 61,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.3280415856061,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.38802948398163,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 19.750063500095248,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 146,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:qwen-qwen3-8-27b:395c64922f7fe00a",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "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": "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": 69,
      "max_score": null,
      "measured_at": "2026-09-10T07:03:39Z",
      "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": 145,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.9893251701199,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.009010479559414,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 212,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:claude-sonnet-5:765bc291b12a711e",
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "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-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": 69,
      "max_score": null,
      "measured_at": "2026-09-10T08:12:13Z",
      "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": 212,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.3066313675868,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.86599146220886,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 1,
      "attempted_matches": 196,
      "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": 95,
      "draws": 30,
      "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": 99,
      "max_score": null,
      "measured_at": "2026-09-10T10:54:56Z",
      "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": 190,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.207793643488,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.071697400705354,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 168,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:deepseek-deepseek-v4-flash:23183d74d990acfd",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 84,
      "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": "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": 34,
      "max_score": null,
      "measured_at": "2026-09-10T06:53:31Z",
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.6499572297143,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.01785125489565,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 21.644413988924462,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:claude-opus-4-8:0b9e44df31643ae8",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "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-opus-4-8",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T10:31:14Z",
      "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": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.0280879589282,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.01106956211032,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 494,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:google-gemini-3-6-flash:157bc5e3bd81a2f8",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 186,
      "draws": 125,
      "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": 215,
      "max_score": null,
      "measured_at": "2026-09-10T10:59:04Z",
      "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": 492,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.8610019118303,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.56614014388901,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 268,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:meituan-longcat-2-0:26225fa06d2cccd9",
      "capped_draws": 38,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 91,
      "draws": 123,
      "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": 81,
      "max_score": null,
      "measured_at": "2026-09-10T08:26:41Z",
      "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": 267,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.2272237880622,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.878168765270942,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 1,
      "attempted_matches": 257,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5-6-luna:56b3e8082c8d4caf",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 94,
      "draws": 103,
      "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": 84,
      "max_score": null,
      "measured_at": "2026-09-10T11:01:12Z",
      "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": 257,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.6322402370815,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.559379754277902,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5-5:fc52395a742e5644",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "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-5.5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T11:59:49Z",
      "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": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.4311911915072,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.16793741587809,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 298,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5-4:91029345b4b373cd",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "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": "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": 83,
      "max_score": null,
      "measured_at": "2026-09-10T08:14:09Z",
      "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": 292,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.118451422626,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.79281756153531,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 499,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:google-gemini-3-5-flash-lite:ada8852a63812f17",
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 178,
      "draws": 233,
      "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": 162,
      "max_score": null,
      "measured_at": "2026-09-10T10:48:47Z",
      "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": 499,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.7777990120844,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.622810270087797,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 104
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:tencent-hy4-preview:a81918b0d5baba2a",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 93,
      "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": 25,
      "max_score": null,
      "measured_at": "2026-09-10T10:52:41Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.3610086540643,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.53664270722644,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:nex-agi-nex-n2-pro:ef6c9f2b08b0d606",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 22,
      "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": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 16,
      "max_score": null,
      "measured_at": "2026-08-04T08:55:37Z",
      "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": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.750666950453,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.11331182821081,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 27.678571428571434,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:x-ai-grok-build-0-1:32469550859abedd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 19,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 17,
      "max_score": null,
      "measured_at": "2026-08-03T12:01:44Z",
      "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": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.2542829519666,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.075364138283934,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 26.264004201400486,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 536,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:poolside-laguna-s-2-1:df6bf1faab8cda70",
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 186,
      "draws": 223,
      "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": 201,
      "max_score": null,
      "measured_at": "2026-09-10T10:57:42Z",
      "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": 536,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.963147228935,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.00561511750182,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "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": 66,
      "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": "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": 42,
      "max_score": null,
      "measured_at": "2026-09-10T10:55:16Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.9860745205874,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.04102891334411,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 46,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5:2447de160165f34c",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 22,
      "draws": 24,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:53:39Z",
      "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": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.8505029015237,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.750002522868716,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 145,
      "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": 68,
      "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": "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": 41,
      "max_score": null,
      "measured_at": "2026-09-10T10:54:12Z",
      "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": 145,
      "rating_method": "sequential_elo",
      "raw_elo": 1384.5499476251923,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.327712683660216,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:deepseek-deepseek-v4-pro:768bc94990435e72",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "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": "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": 59,
      "max_score": null,
      "measured_at": "2026-09-10T10:50:08Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1385.0409301782825,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.214390866699837,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:openai-gpt-oss-120b:8fc70fdaca40b3e0",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 63,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-09-10T10:52:53Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1370.6296442485063,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.714994916497854,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:cohere-north-mini-code:568529666a0f96d5",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 10,
      "draws": 17,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 18,
      "max_score": null,
      "measured_at": "2026-08-05T04:21:17Z",
      "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": 38,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.8618585327608,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.98682614510266,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 68.15840602663853,
      "unilateral_faults": null,
      "wins": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 168,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:z-ai-glm-5-2:ce87a33d1a10c901",
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 84,
      "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": "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": 59,
      "max_score": null,
      "measured_at": "2026-09-10T10:59:37Z",
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1364.168727478889,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.42619957772019,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 19.224746826339327,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03: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": 66,
      "draws": 78,
      "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": 42,
      "max_score": null,
      "measured_at": "2026-09-10T10:58:30Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1330.0461612539777,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.492560475629574,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:claude-fable-5:4fee988c3b8ad119",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 45,
      "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": 75,
      "max_score": null,
      "measured_at": "2026-09-10T10:58:55Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1235.3161010419403,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.636544202241724,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 114,
      "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": 57,
      "draws": 14,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-09-10T10:10:05Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1883.1951086512008,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 94.27440970618706,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "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": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-09-10T10:09:42Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1826.3218602875163,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 84.862183400186,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 186,
      "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": 76,
      "draws": 43,
      "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": 21,
      "max_score": null,
      "measured_at": "2026-09-10T10:00:41Z",
      "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": 186,
      "rating_method": "sequential_elo",
      "raw_elo": 1740.1002470017625,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 71.92507204628161,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 114,
      "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": 57,
      "draws": 20,
      "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": 40,
      "max_score": null,
      "measured_at": "2026-09-10T09:57:26Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1636.7722908196843,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.49271716840484,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "draws": 44,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-09-10T09:57:01Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1632.0099106719301,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 52.70456806499455,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5-4-nano:65879fd5791a5546",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 46,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:04:11Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1590.6223690206723,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.28025300648413,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5-4-mini:b89689b888a03e98",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "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-5.4-mini",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:11:05Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1575.2825468133171,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.14931890005339,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:xiaomi-mimo-v2-5-pro:43c3a8c0c343b927",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "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-v2.5-pro",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 12,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:01Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.6849655511323,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.69028173978519,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "draws": 38,
      "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": 40,
      "max_score": null,
      "measured_at": "2026-09-10T09:50:58Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.1136000673366,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.48214490364818,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 362,
      "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": 181,
      "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": "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": 118,
      "max_score": null,
      "measured_at": "2026-09-10T09:52:47Z",
      "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": 362,
      "rating_method": "sequential_elo",
      "raw_elo": 1541.4198741744876,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.87091498905499,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.9168269413437915,
      "unilateral_faults": 0,
      "wins": 99
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 146,
      "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": 73,
      "draws": 66,
      "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": 34,
      "max_score": null,
      "measured_at": "2026-08-05T03:57:28Z",
      "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": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1548.6162307333443,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.38045751660635,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 14.377800258513929,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "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": "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": 35,
      "max_score": null,
      "measured_at": "2026-09-10T09:50:27Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1533.4049458340203,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 36.38596009636121,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5:2447de160165f34c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 48,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:03:31Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1534.830093500697,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.04692207446579,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "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": 67,
      "draws": 63,
      "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": 40,
      "max_score": null,
      "measured_at": "2026-09-10T00:27:17Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.4638147130581,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.568416069453946,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:qwen-qwen3-7-max:1ec5e86937e80891",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 52,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 16,
      "max_score": null,
      "measured_at": "2026-08-05T05:03:39Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.912180056845,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.82886597508527,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:minimax-minimax-m3:31a675d7727a5125",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 59,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 3,
      "max_score": null,
      "measured_at": "2026-08-05T04:04:06Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1506.5088333178212,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.138488502474974,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 140,
      "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": 70,
      "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": "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": 44,
      "max_score": null,
      "measured_at": "2026-09-10T05:33:29Z",
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.2374098132043,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.674580273173802,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:stepfun-step-3-7-flash:bf3021406df8f368",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 61,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:11:10Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.9648602725551,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.646329769358474,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "draws": 58,
      "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": 33,
      "max_score": null,
      "measured_at": "2026-09-10T09:45:32Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.3894653501343,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.432616968483536,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 190,
      "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": 78,
      "draws": 122,
      "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": 42,
      "max_score": null,
      "measured_at": "2026-09-10T02:20:20Z",
      "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": 190,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.5368821382333,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.350634971233603,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:google-gemini-3-1-flash-lite:a27c54e25bfb4de0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "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-3.1-flash-lite",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T03:46:58Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.4791598953682,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.022538939196433,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 2,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:moonshotai-kimi-k2-7-code:bad3fe5c7b1e8a5f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 58,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 7,
      "max_score": null,
      "measured_at": "2026-08-05T01:17:06Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.0137499861821,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.795545497153316,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:cohere-north-mini-code:568529666a0f96d5",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 24,
      "draws": 69,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 5,
      "max_score": null,
      "measured_at": "2026-08-05T01:16:32Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.3158309109629,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.751123392297373,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 35.48369970321018,
      "unilateral_faults": null,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 188,
      "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": 94,
      "draws": 96,
      "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": 59,
      "max_score": null,
      "measured_at": "2026-09-10T03:14:23Z",
      "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": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.996413725924,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.5668099847064,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.834993123162105,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:google-gemma-4-31b-it:dee0b5fdcae9fd5f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 55,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 2,
      "max_score": null,
      "measured_at": "2026-08-04T02:50:00Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.0433924004185,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.208177713775562,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 2,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:x-ai-grok-build-0-1:32469550859abedd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 65,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 5,
      "max_score": null,
      "measured_at": "2026-08-05T03:57:28Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.6086038147535,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.170519861988716,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 82,
      "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": 40,
      "draws": 59,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-08-05T00:15:53Z",
      "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": 81,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.3132261970989,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.62770249214871,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "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": 43,
      "draws": 66,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-08-05T05:10:34Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.6741891937638,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.656853491070645,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:claude-opus-4-8:0b9e44df31643ae8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 69,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:15:12Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.2736621572235,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.09637172241155,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 198,
      "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": 81,
      "draws": 109,
      "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": 59,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:17Z",
      "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": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.1966197661275,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.592241653411964,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 271,
      "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": 98,
      "draws": 191,
      "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": 39,
      "max_score": null,
      "measured_at": "2026-09-10T09:56:32Z",
      "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": 267,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.1765238688329,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.748427314763532,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 130,
      "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": 65,
      "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-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": "2026-09-10T07:15:52Z",
      "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": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.8661207582813,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.611947649463634,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 114,
      "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": 57,
      "draws": 85,
      "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": 21,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:17Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.061245609558,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.58598065433972,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5-5:fc52395a742e5644",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "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-5.5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:28:39Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.3238586920036,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.27457919744084,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:o3:9e4cf63e80682b9b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 51,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T11:49:23Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.7140351902344,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.72518278425092,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 8
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 210,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:xiaomi-mimo-v2-5:9e3a1125fb872e8c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 100,
      "draws": 163,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 38,
      "max_score": null,
      "measured_at": "2026-08-03T11:50:25Z",
      "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": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.6010053359187,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.692328669404453,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 15.29978989793973,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "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": 63,
      "draws": 84,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:34Z",
      "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": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.2604001496738,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.42835891103803,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 178,
      "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": 89,
      "draws": 143,
      "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": 25,
      "max_score": null,
      "measured_at": "2026-09-10T04:42:34Z",
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.8038436465395,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 21.796361705747216,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 12.320672898160003,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 337,
      "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": 133,
      "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": "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": 35,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:54Z",
      "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": 327,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.4959236408645,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 21.30546578772129,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.640518153991441,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "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": 59,
      "draws": 95,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-09-10T07:14:29Z",
      "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": 127,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.633225132272,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.5271127751659,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.444173824159213,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 184,
      "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": 89,
      "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": "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": 46,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:54Z",
      "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": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.112805928553,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.26667941148646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 1,
      "attempted_matches": 114,
      "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": 57,
      "draws": 92,
      "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": 10,
      "max_score": null,
      "measured_at": "2026-09-10T00:27:30Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.3664247023332,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.161095610049934,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 337,
      "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": 135,
      "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": "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": 51,
      "max_score": null,
      "measured_at": "2026-09-10T09:51:11Z",
      "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": 337,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.4671288080813,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 19.256845011483584,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.0009297552497305,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "draws": 78,
      "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": 21,
      "max_score": null,
      "measured_at": "2026-09-10T07:15:45Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.8842293634966,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 19.25382084260791,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "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": 64,
      "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": "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": 23,
      "max_score": null,
      "measured_at": "2026-09-10T04:42:36Z",
      "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": 127,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.6094997952396,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 18.70274366327956,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.444173824159213,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "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": "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": 16,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:50Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.2957587674696,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.99796849337146,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 222,
      "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": 79,
      "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": "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": 28,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:21Z",
      "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": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.148036085779,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.562136050360625,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:inclusionai-ling-3-0-flash:0cd16c129bab6df2",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 21,
      "draws": 203,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 39,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:54Z",
      "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": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.2708927832791,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.068321646037397,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 184,
      "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": 68,
      "draws": 101,
      "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": 53,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:53Z",
      "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": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1390.1989659365513,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 13.992136416293384,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 250,
      "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": 86,
      "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": "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": 71,
      "max_score": null,
      "measured_at": "2026-09-10T09:49:00Z",
      "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": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1368.0246720541775,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 11.01099847514966,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 186,
      "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": 68,
      "draws": 104,
      "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": 62,
      "max_score": null,
      "measured_at": "2026-09-10T09:52:12Z",
      "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": 186,
      "rating_method": "sequential_elo",
      "raw_elo": 1362.819635098196,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 9.48709633237125,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 114,
      "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": 57,
      "draws": 73,
      "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": 28,
      "max_score": null,
      "measured_at": "2026-09-10T09:50:49Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1369.3199862945683,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 9.230754142229273,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "draws": 80,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-09-10T09:50:45Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1363.6054976163036,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 8.285036037313507,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 491,
      "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": 166,
      "draws": 277,
      "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": 141,
      "max_score": null,
      "measured_at": "2026-09-10T09:51:03Z",
      "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": 458,
      "rating_method": "sequential_elo",
      "raw_elo": 1336.279199723666,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 5.565460776989309,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 33,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "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-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": 50,
      "max_score": null,
      "measured_at": "2026-09-10T09:56:32Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1313.5432809915524,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:29Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 2007.3708129337665,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 88.69644055635243,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 103
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 10,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:27Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1992.4645295287164,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 87.52798814855652,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 154,
      "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": 77,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-08-05T05:35:16Z",
      "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": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1864.477227519094,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 76.79549207854782,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 12.867341638060083,
      "unilateral_faults": 0,
      "wins": 134
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "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": 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-5.6-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": 58,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:05Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1841.9988908139892,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 76.41507877251388,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 208,
      "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": 82,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:27Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1818.8623378508958,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 74.60148377480539,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 139
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 31,
      "max_score": null,
      "measured_at": "2026-09-10T10:38:56Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1820.235845616354,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 74.02757258952171,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 524,
      "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": 198,
      "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": 141,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:25Z",
      "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": 524,
      "rating_method": "sequential_elo",
      "raw_elo": 1790.0700567199,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 72.57999142955795,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 383
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 48,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:16Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1737.7777429081157,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 67.56396485889975,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:x-ai-grok-build-0-1:32469550859abedd",
      "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": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 37,
      "max_score": null,
      "measured_at": "2026-08-05T05:34:43Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1718.4606854659032,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 65.57660382357807,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5-5:fc52395a742e5644",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:43:10Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1681.0811589466743,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 62.139557449757454,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "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": 67,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:42Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1660.04663503317,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 61.62273404542139,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 120,
      "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": 60,
      "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": 62,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:46Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1660.6856082501972,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 61.52097695135376,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:qwen-qwen3-7-plus:d327d3640f27bd3b",
      "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": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 48,
      "max_score": null,
      "measured_at": "2026-08-05T03:48:47Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1657.1023897142595,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 60.93926279553979,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5:2447de160165f34c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:41:12Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1661.473206220661,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 60.71202505477096,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "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": 44,
      "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": 31,
      "max_score": null,
      "measured_at": "2026-08-04T21:09:49Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1643.1446974256544,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 59.672841954852146,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 59,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:33Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1630.175690041946,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 59.12940915250124,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:google-gemma-4-31b-it:dee0b5fdcae9fd5f",
      "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": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 45,
      "max_score": null,
      "measured_at": "2026-08-05T03:57:18Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1608.0684118194988,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 57.095657519959566,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 61,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:15Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1586.236607414437,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.68517523467149,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:claude-opus-4-8:0b9e44df31643ae8",
      "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": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:49:27Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1589.0366798457355,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.57150390760981,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:moonshotai-kimi-k2-7-code:bad3fe5c7b1e8a5f",
      "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": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 40,
      "max_score": null,
      "measured_at": "2026-08-05T05:26:21Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1589.1184862164962,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.31987902290327,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "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": 67,
      "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": 74,
      "max_score": null,
      "measured_at": "2026-09-10T07:08:52Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1578.0415953119314,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.194640367743276,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:o3:9e4cf63e80682b9b",
      "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": "o3",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:51:41Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1579.92232517005,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.753782941211256,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 264,
      "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": 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": "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": 138,
      "max_score": null,
      "measured_at": "2026-09-10T07:11:36Z",
      "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": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1554.5881102767514,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.128679364952525,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5-4-mini:b89689b888a03e98",
      "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-5.4-mini",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:08:36Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.90982985875,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.75866949290433,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:qwen-qwen3-7-max:1ec5e86937e80891",
      "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": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 49,
      "max_score": null,
      "measured_at": "2026-08-05T03:00:43Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1560.9179428825034,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.46148943250204,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 140,
      "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": 70,
      "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": 80,
      "max_score": null,
      "measured_at": "2026-09-10T10:25:33Z",
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.5287428396603,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.252816096613515,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 316,
      "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": 107,
      "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": 131,
      "max_score": null,
      "measured_at": "2026-09-10T07:08:46Z",
      "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": 316,
      "rating_method": "sequential_elo",
      "raw_elo": 1533.0248082619837,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 52.6034542376244,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 330,
      "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": 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": "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": 151,
      "max_score": null,
      "measured_at": "2026-09-10T08:08:59Z",
      "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": 330,
      "rating_method": "sequential_elo",
      "raw_elo": 1532.290670637824,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 52.5835528465637,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 196,
      "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": 98,
      "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": 120,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:35Z",
      "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": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1550.3347621659645,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 52.29644206798784,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.834993123162105,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 140,
      "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": 70,
      "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": 80,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:46Z",
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.634012263492,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.98785731400378,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 156,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5-4-nano:65879fd5791a5546",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 77,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:42:37Z",
      "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": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1530.8163667007361,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.607779083394135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.396498219564457,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:stepfun-step-3-7-flash:bf3021406df8f368",
      "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": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:51:39Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.1946829738897,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.98510602874532,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:cohere-north-mini-code:568529666a0f96d5",
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 44,
      "max_score": null,
      "measured_at": "2026-08-05T02:08:01Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.461307692719,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.11080098947388,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 26.824399540348086,
      "unilateral_faults": null,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 142,
      "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": 71,
      "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": 53,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:13Z",
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.6092653665523,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.574464166754886,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 136,
      "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": 68,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-09-10T05:27:40Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.0833874264852,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.45741606820675,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 164,
      "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": 82,
      "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": 62,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:33Z",
      "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": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.1691456804797,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.761351709774466,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 190,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:xiaomi-mimo-v2-5:9e3a1125fb872e8c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 94,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 98,
      "max_score": null,
      "measured_at": "2026-08-04T22:17:40Z",
      "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": 190,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.241945584617,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.99727906392186,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.450315194658201,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 220,
      "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": 82,
      "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": 91,
      "max_score": null,
      "measured_at": "2026-09-10T07:11:12Z",
      "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": 220,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.8378450569335,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.42107820004769,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 129
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 146,
      "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": 73,
      "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": 55,
      "max_score": null,
      "measured_at": "2026-09-10T06:05:41Z",
      "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": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.2778157227672,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.29216666489487,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 207,
      "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": 80,
      "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": 99,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:13Z",
      "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": 207,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.6706022597677,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.951124002900116,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 128,
      "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": 64,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-09-10T07:08:54Z",
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.282174092201,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.86378827356518,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 81
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 406,
      "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": 203,
      "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": 198,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:22Z",
      "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": 406,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.8517046947445,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.3483500632467,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.5681818181818196,
      "unilateral_faults": 0,
      "wins": 208
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "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": 67,
      "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": 54,
      "max_score": null,
      "measured_at": "2026-09-10T08:06:59Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.7633280592884,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.17968294559612,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 562,
      "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": 192,
      "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": 345,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:01Z",
      "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": 562,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.9234581653127,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.612280911763705,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 126,
      "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": 63,
      "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": 50,
      "max_score": null,
      "measured_at": "2026-09-10T04:39:18Z",
      "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": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1412.4135684859086,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.1279310571795,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 266,
      "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": 133,
      "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": 151,
      "max_score": null,
      "measured_at": "2026-09-10T08:14:45Z",
      "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": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.884374010715,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.99995218852661,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.444412180259302,
      "unilateral_faults": 0,
      "wins": 115
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:nex-agi-nex-n2-pro:ef6c9f2b08b0d606",
      "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": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 56,
      "max_score": null,
      "measured_at": "2026-08-04T09:17:51Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1328.357377257976,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.95975901608025,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:xiaomi-mimo-v2-5-pro:43c3a8c0c343b927",
      "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": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 59,
      "max_score": null,
      "measured_at": "2026-08-05T03:42:02Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1322.9127343144567,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.643217642393346,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 33
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 581,
      "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": 195,
      "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": 373,
      "max_score": null,
      "measured_at": "2026-09-10T10:38:59Z",
      "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": 581,
      "rating_method": "sequential_elo",
      "raw_elo": 1273.9436592054853,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.2189735823991,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 120,
      "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": 60,
      "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": 88,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:04Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1267.6313790429688,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.71080462121027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "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": 55,
      "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": 70,
      "max_score": null,
      "measured_at": "2026-08-05T04:51:41Z",
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1258.6306450543475,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.879639110693958,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:google-gemini-3-1-flash-lite:a27c54e25bfb4de0",
      "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": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T21:09:30Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1241.5251670106486,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.987177717585375,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 90,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:05Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1076.3642382857881,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 15.718029757272555,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 542,
      "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": 182,
      "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": 426,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:05Z",
      "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": 542,
      "rating_method": "sequential_elo",
      "raw_elo": 1062.4837451299554,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 15.579243027156668,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 120,
      "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": 60,
      "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": 90,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:06Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1048.5046266155819,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 13.534210393870193,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "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": 62,
      "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": 116,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:33Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1009.4016134129805,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.600689036218679,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:minimax-minimax-m3:31a675d7727a5125",
      "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": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 86,
      "max_score": null,
      "measured_at": "2026-08-04T23:59:53Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 946.7487485340107,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 5.046768034226976,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 11,
      "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": 7,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:04Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 2093.753980134374,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 95.8308881823799,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 100
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 11,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-09-10T10:09:30Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1991.6471169850581,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 87.8458198199057,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 85
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 512,
      "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": 189,
      "draws": 51,
      "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": 81,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:25Z",
      "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": 512,
      "rating_method": "sequential_elo",
      "raw_elo": 1850.8283392924154,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 77.74963744928857,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 380
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-09-10T10:05:14Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1854.3315939739264,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 77.10732678766597,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 8,
      "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": 39,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:12Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1849.1694453365888,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 76.70363100762701,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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": "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": 39,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:17Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1837.9129732888766,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 75.82334053498934,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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-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": 40,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:18Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1836.2178346014025,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 75.69077551550029,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 10,
      "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": 21,
      "max_score": null,
      "measured_at": "2026-09-10T10:02:31Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1817.90041052838,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 74.25829704210302,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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": "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": 37,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:22Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1817.3175803869053,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 74.21271794604775,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 162,
      "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": 81,
      "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": "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": 36,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:07Z",
      "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": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1802.3044945588013,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 72.14085667254591,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.435262050701777,
      "unilateral_faults": 0,
      "wins": 113
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 24,
      "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": 32,
      "max_score": null,
      "measured_at": "2026-09-10T10:01:12Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1790.8162168118583,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 72.14023042347958,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:qwen-qwen3-7-plus:d327d3640f27bd3b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 15,
      "max_score": null,
      "measured_at": "2026-08-03T07:40:51Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1789.1763903140825,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 70.99957787144118,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "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": 85,
      "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-5.4",
        "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": 52,
      "max_score": null,
      "measured_at": "2026-09-10T09:56:14Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1766.52793989414,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 70.9445905573761,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 140
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:claude-opus-4-8:0b9e44df31643ae8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T08:42:55Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1783.9848192621998,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 70.46838917607434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:xiaomi-mimo-v2-5-pro:43c3a8c0c343b927",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 19,
      "max_score": null,
      "measured_at": "2026-08-03T05:25:24Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1773.266695390409,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 70.02330483752023,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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": "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": 56,
      "max_score": null,
      "measured_at": "2026-09-10T10:00:40Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1757.9430530119864,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 69.56944867447089,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 158,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5-4-nano:65879fd5791a5546",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 78,
      "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-5.4-nano",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T06:55:07Z",
      "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": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1644.7113224940283,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 60.07944202124918,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 12.233820686813306,
      "unilateral_faults": 0,
      "wins": 102
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 332,
      "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": 118,
      "draws": 32,
      "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": 165,
      "max_score": null,
      "measured_at": "2026-09-10T05:52:53Z",
      "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": 332,
      "rating_method": "sequential_elo",
      "raw_elo": 1621.172337112724,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 60.02690569508898,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:qwen-qwen3-7-max:1ec5e86937e80891",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 10,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 25,
      "max_score": null,
      "measured_at": "2026-08-05T05:35:11Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1629.0069225523212,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 59.000095631169074,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:nvidia-nemotron-3-ultra-550b-a55b:3bcb1a7b4e915226",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 7,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:41:43Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1630.394611108272,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 58.942903698869344,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:o3:9e4cf63e80682b9b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 8,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:57:23Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1620.6162562438012,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 58.26405875417527,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5:2447de160165f34c",
      "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": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:03:53Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1601.8729234393843,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 56.83890819619163,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5-4-mini:b89689b888a03e98",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 10,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:53:50Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1591.3433947162612,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 56.015466910410275,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 160,
      "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": 74,
      "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": "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": 84,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:07Z",
      "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": 160,
      "rating_method": "sequential_elo",
      "raw_elo": 1543.9232121385512,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.23468310597876,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 176,
      "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": 88,
      "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": "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": 101,
      "max_score": null,
      "measured_at": "2026-09-10T09:56:14Z",
      "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": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.6481680538632,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.0144266368767,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 232,
      "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": 87,
      "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-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": 108,
      "max_score": null,
      "measured_at": "2026-09-10T09:59:54Z",
      "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": 231,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.7437375270322,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 51.75536719315471,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 114
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 168,
      "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": 84,
      "draws": 7,
      "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": 81,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:24Z",
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.7368874771566,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.69846903136761,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 326,
      "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": 109,
      "draws": 29,
      "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": 155,
      "max_score": null,
      "measured_at": "2026-09-10T10:09:09Z",
      "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": 326,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.2475127581479,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.63276325737119,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5-5:fc52395a742e5644",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 1,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T09:49:28Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.4542538973014,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.5623612264452,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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": 45,
      "max_score": null,
      "measured_at": "2026-09-10T09:44:31Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.0349225157022,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.91438765370183,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 146,
      "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": 73,
      "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-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": 65,
      "max_score": null,
      "measured_at": "2026-09-10T07:31:24Z",
      "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": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.3776071905042,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.66463879800661,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 146,
      "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": 73,
      "draws": 11,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-09-10T07:23:54Z",
      "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": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.7153447051658,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.2051929082044,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 104,
      "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": 50,
      "draws": 7,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-08-05T04:57:37Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.2718722969803,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.7593724232428,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:x-ai-grok-build-0-1:32469550859abedd",
      "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": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 53,
      "max_score": null,
      "measured_at": "2026-08-03T12:10:00Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.1758902452225,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.47206803669905,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:google-gemini-3-1-flash-lite:a27c54e25bfb4de0",
      "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": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T10:58:16Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.4761224416814,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.02538255150319,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "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": 69,
      "draws": 16,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-09-10T02:26:33Z",
      "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": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1390.83708850739,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.07494801160975,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:google-gemma-4-31b-it:dee0b5fdcae9fd5f",
      "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": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 56,
      "max_score": null,
      "measured_at": "2026-08-03T13:20:46Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1375.9572202695874,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.24873264001045,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 32
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 286,
      "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": 143,
      "draws": 6,
      "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": 141,
      "max_score": null,
      "measured_at": "2026-09-10T00:52:26Z",
      "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": 286,
      "rating_method": "sequential_elo",
      "raw_elo": 1370.7779398356788,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 38.93697150240678,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.403223864214983,
      "unilateral_faults": 0,
      "wins": 139
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:xiaomi-mimo-v2-5:9e3a1125fb872e8c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "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-v2.5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 58,
      "max_score": null,
      "measured_at": "2026-08-05T04:57:10Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1369.4305277949966,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 38.84474260375074,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:minimax-minimax-m3:31a675d7727a5125",
      "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": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 57,
      "max_score": null,
      "measured_at": "2026-08-05T01:46:15Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1363.2498048504203,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 38.29161379644027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 214,
      "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": 77,
      "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-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": 107,
      "max_score": null,
      "measured_at": "2026-09-10T04:44:07Z",
      "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": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1333.976725690619,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.148171051976554,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:cohere-north-mini-code:568529666a0f96d5",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 27,
      "draws": 1,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 55,
      "max_score": null,
      "measured_at": "2026-08-05T02:42:09Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1356.0188073823756,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 36.17363038802949,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 33.47940711208657,
      "unilateral_faults": null,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "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": 81,
      "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-5.6-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": 121,
      "max_score": null,
      "measured_at": "2026-09-10T04:44:38Z",
      "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": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1302.406805806133,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.76336759556245,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:stepfun-step-3-7-flash:bf3021406df8f368",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "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": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T23:37:39Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1271.9140813081422,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.07434547943685,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 25
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 562,
      "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": 188,
      "draws": 39,
      "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": 353,
      "max_score": null,
      "measured_at": "2026-09-10T10:01:16Z",
      "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": 562,
      "rating_method": "sequential_elo",
      "raw_elo": 1248.2559899500977,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.7144277981412,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:inclusionai-ling-3-0-flash:0cd16c129bab6df2",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "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": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 208,
      "max_score": null,
      "measured_at": "2026-09-10T10:02:24Z",
      "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": 292,
      "rating_method": "sequential_elo",
      "raw_elo": 1243.933403264033,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.963264231692612,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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": 70,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:25Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1207.1538729649988,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.49605360253772,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:nex-agi-nex-n2-pro:ef6c9f2b08b0d606",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 9,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 59,
      "max_score": null,
      "measured_at": "2026-08-05T05:35:20Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1211.2987002752848,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.254176503754234,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 14
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 310,
      "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": 147,
      "draws": 20,
      "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": 192,
      "max_score": null,
      "measured_at": "2026-09-10T10:25:37Z",
      "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": 310,
      "rating_method": "sequential_elo",
      "raw_elo": 1149.9302789153699,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.36329166385045,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 98
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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": 82,
      "max_score": null,
      "measured_at": "2026-09-10T10:05:29Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1134.8331246095388,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.84035033409872,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 137,
      "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": 63,
      "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": 95,
      "max_score": null,
      "measured_at": "2026-09-10T10:02:48Z",
      "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": 137,
      "rating_method": "sequential_elo",
      "raw_elo": 1129.6109725111855,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.636672560776855,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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": 80,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:04Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1130.7908652219028,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.524233311661888,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 284,
      "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": 96,
      "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": "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": 201,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:23Z",
      "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": 284,
      "rating_method": "sequential_elo",
      "raw_elo": 1112.70739237112,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.124655747942903,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 532,
      "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": 180,
      "draws": 7,
      "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": 428,
      "max_score": null,
      "measured_at": "2026-09-10T10:09:06Z",
      "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": 532,
      "rating_method": "sequential_elo",
      "raw_elo": 1063.2432752679865,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 16.1949707891289,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-09-10T10:09:47Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1004.422711902854,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.641858004366158,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:47Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 2100.234118121552,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 115
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 6,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:17Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 2051.5484644930266,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 95.94419593771026,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 118
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 132,
      "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": 66,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-05T04:43:15Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1839.0854245052378,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 77.13223675647313,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 17.664741204687253,
      "unilateral_faults": 0,
      "wins": 108
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 51,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:14Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1770.5152776722223,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 72.53246258720579,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:09Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1764.710116676486,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 72.04885820287524,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 56,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:19Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1762.832763073679,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 71.89246349927906,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:qwen-qwen3-7-max:1ec5e86937e80891",
      "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": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 10,
      "max_score": null,
      "measured_at": "2026-08-05T02:27:25Z",
      "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": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1775.8567877936537,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 71.61968219996771,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:24Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1756.8345831771405,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 71.39277949428767,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 51,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:18Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1735.5902511796148,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 69.62300048148802,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 57,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:15Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1730.9511982705933,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 69.23653982560063,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:claude-opus-4-8:0b9e44df31643ae8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:31:22Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1738.437095863048,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 68.88596501989264,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:21Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1708.102176119845,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 67.33308059374065,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5-5:fc52395a742e5644",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:27:48Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1708.9421639300028,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 66.31252434317867,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 55,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:35Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1686.0872386532578,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 65.49910556920233,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5:2447de160165f34c",
      "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": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:28:28Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1690.0437032215139,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 64.90905738242017,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:o3:9e4cf63e80682b9b",
      "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": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:17:46Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1685.7742661744414,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 64.65603985716929,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 210,
      "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": 87,
      "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": 71,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:37Z",
      "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": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1629.7367324775714,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 61.491210707100855,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 139
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "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": 85,
      "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": 99,
      "max_score": null,
      "measured_at": "2026-09-10T10:25:59Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1620.0527433433303,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 60.67352692884251,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 109
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "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": 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": "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": 32,
      "max_score": null,
      "measured_at": "2026-08-05T02:27:33Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1628.2563386094778,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 60.08935840000744,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 168,
      "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": 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": "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": 98,
      "max_score": null,
      "measured_at": "2026-09-10T10:38:58Z",
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.3496621939992,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.77515547852249,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 192,
      "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": 96,
      "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": 90,
      "max_score": null,
      "measured_at": "2026-09-10T05:24:20Z",
      "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": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.420023753623,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.68417033513214,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.834993123162105,
      "unilateral_faults": 0,
      "wins": 102
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "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": 69,
      "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": 76,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:37Z",
      "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": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1551.253062152687,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.42069483699623,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 201,
      "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": 94,
      "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": 102,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:25Z",
      "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": 201,
      "rating_method": "sequential_elo",
      "raw_elo": 1541.4606321797407,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.086740109183,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 99
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "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": 68,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:19Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1521.2495664877445,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 51.90066980814227,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 270,
      "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": 102,
      "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": 123,
      "max_score": null,
      "measured_at": "2026-09-10T04:41:01Z",
      "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": 270,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.6086176884314,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.753970891959106,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 147
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:moonshotai-kimi-k2-7-code:bad3fe5c7b1e8a5f",
      "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": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 40,
      "max_score": null,
      "measured_at": "2026-08-05T05:26:41Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.4961528383703,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.35863516788991,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 130,
      "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": 65,
      "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": 55,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:35Z",
      "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": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.9116984620532,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.3085497072,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 354,
      "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": 121,
      "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": 180,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:29Z",
      "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": 354,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.3897304730226,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.57515742958389,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 378,
      "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": 153,
      "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": 177,
      "max_score": null,
      "measured_at": "2026-09-10T07:08:49Z",
      "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": 378,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.5103578202652,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.90130757412859,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.293412226141589,
      "unilateral_faults": 0,
      "wins": 201
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:xiaomi-mimo-v2-5-pro:43c3a8c0c343b927",
      "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": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 46,
      "max_score": null,
      "measured_at": "2026-08-05T04:43:24Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.1477983527448,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.60664400355754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:minimax-minimax-m3:31a675d7727a5125",
      "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": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 45,
      "max_score": null,
      "measured_at": "2026-08-05T03:34:26Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.1227460326932,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.5556009285104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5-4-mini:b89689b888a03e98",
      "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": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:19:10Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.4064114364373,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.02249928924504,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:nex-agi-nex-n2-pro:ef6c9f2b08b0d606",
      "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": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 41,
      "max_score": null,
      "measured_at": "2026-08-05T00:37:00Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.0240469090763,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.74072823827207,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:qwen-qwen3-7-plus:d327d3640f27bd3b",
      "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": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 45,
      "max_score": null,
      "measured_at": "2026-08-03T15:18:37Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.8109077124877,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.42393579584542,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:google-gemma-4-31b-it:dee0b5fdcae9fd5f",
      "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": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 40,
      "max_score": null,
      "measured_at": "2026-08-04T21:46:04Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.0882405137008,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.954865800457036,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 44
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 156,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:xiaomi-mimo-v2-5:9e3a1125fb872e8c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 75,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 76,
      "max_score": null,
      "measured_at": "2026-08-04T23:37:48Z",
      "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": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.689002618837,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.02896848324199,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 12.626594026364666,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "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:0cd16c129bab6df2",
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 342,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:32Z",
      "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": 592,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.556676770801,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.412761651647685,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 250
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 396,
      "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": 198,
      "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": 207,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:29Z",
      "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": 396,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.2360449335408,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.26903335828475,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.6475730333305307,
      "unilateral_faults": 0,
      "wins": 189
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 152,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5-4-nano:65879fd5791a5546",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 75,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:34:28Z",
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.6299185770467,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.15012153636137,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.244710982631887,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:cohere-north-mini-code:568529666a0f96d5",
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 52,
      "max_score": null,
      "measured_at": "2026-08-05T05:19:01Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.9512232436878,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.60735748459359,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 26.79047988958712,
      "unilateral_faults": null,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 61,
      "max_score": null,
      "measured_at": "2026-09-10T10:25:58Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1403.884604633261,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.98995032235631,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 212,
      "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": 77,
      "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": 112,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:08Z",
      "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": 212,
      "rating_method": "sequential_elo",
      "raw_elo": 1389.9379293174322,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.52534176853236,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 100
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 148,
      "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": 71,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-09-10T07:08:48Z",
      "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": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.6769732770667,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.30685657778837,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 262,
      "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": 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": "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": 140,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:14Z",
      "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": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1399.6303650912164,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.03113787699098,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.834993123162105,
      "unilateral_faults": 0,
      "wins": 122
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 572,
      "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": 205,
      "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": 356,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:01Z",
      "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": 572,
      "rating_method": "sequential_elo",
      "raw_elo": 1375.6177949642233,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 40.64504874231809,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "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": 62,
      "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": 58,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:14Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1378.0542771114426,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.83813064889331,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 86,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:24Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1277.4160766202162,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.45437091777823,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 266,
      "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": 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": "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": 180,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:21Z",
      "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": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1265.4548452950958,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.399076922756784,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:x-ai-grok-build-0-1:32469550859abedd",
      "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": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 54,
      "max_score": null,
      "measured_at": "2026-08-05T01:38:57Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1276.8149612185298,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.72713242170736,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "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": 80,
      "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": 132,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:38Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1252.9129029601745,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.08859800058072,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 266,
      "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": 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": "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": 190,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:20Z",
      "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": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1208.9920377589156,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.69538975608495,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:nvidia-nemotron-3-ultra-550b-a55b:3bcb1a7b4e915226",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T23:43:45Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1176.2953930743706,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.05622295359803,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 88,
      "max_score": null,
      "measured_at": "2026-09-10T10:38:59Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1127.7345872672606,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 18.985013985665347,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 266,
      "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": 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": "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": 225,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:04Z",
      "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": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1075.9620883310313,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 15.613204983285852,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:google-gemini-3-1-flash-lite:a27c54e25bfb4de0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:39:12Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1076.1156014586118,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 13.765200753063453,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 105,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:00Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1039.7885406295645,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 11.658586041674393,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 118,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:47Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 899.8395013993829,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 61,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:08Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 2015.5208557563683,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 86.09465836643398,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 102
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 61,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-09-10T10:25:38Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1965.2290624670259,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 81.45581003407503,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 109
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:x-ai-grok-4-5:9ade9c53df23b855",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "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-4.5",
        "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": 10,
      "max_score": null,
      "measured_at": "2026-08-04T23:52:07Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1906.4614489539558,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 75.36004018487888,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 61,
      "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": 26,
      "max_score": null,
      "measured_at": "2026-09-10T10:08:58Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1893.5285342223358,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 74.84224837474918,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 61,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-09-10T10:15:28Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1885.1060573978139,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 74.06537027960984,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 106
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 156,
      "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": 78,
      "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": 19,
      "max_score": null,
      "measured_at": "2026-08-05T05:26:16Z",
      "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": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1877.7575378139375,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 72.56224223151698,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 12.51792189268726,
      "unilateral_faults": 0,
      "wins": 137
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 61,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-09-10T10:08:54Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1843.3344616499016,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 70.21241367175236,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 99
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 61,
      "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": 36,
      "max_score": null,
      "measured_at": "2026-09-10T10:09:00Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1803.034470342118,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 66.49519590628826,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 61,
      "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": 33,
      "max_score": null,
      "measured_at": "2026-09-10T10:05:51Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1758.5557003334645,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 62.39253313399566,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:meta-muse-spark-1-3:b928c7e11b83bab6",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 8,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-09-10T10:02:54Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1729.0069973801026,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 59.66699995147499,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 276,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:claude-opus-4-5:6145092901d96725",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "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": 67,
      "max_score": null,
      "measured_at": "2026-09-09T11:45:10Z",
      "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": 276,
      "rating_method": "sequential_elo",
      "raw_elo": 1710.8842433394993,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 59.105299689263475,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 204
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:google-gemini-3-6-flash:157bc5e3bd81a2f8",
      "capped_draws": 47,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 96,
      "draws": 47,
      "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": 89,
      "max_score": null,
      "measured_at": "2026-09-10T11:10:23Z",
      "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": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1707.404877029335,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 58.67238008178089,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:moonshotai-kimi-k2-7-code:bad3fe5c7b1e8a5f",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 6,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 23,
      "max_score": null,
      "measured_at": "2026-08-03T11:19:09Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1668.9996561249077,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.14046672619939,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:qwen-qwen3-8-max:2315ff339b0c18d0",
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "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": "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": 54,
      "max_score": null,
      "measured_at": "2026-09-10T09:55:40Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1632.9127357518287,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.977952428863446,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:meta-muse-spark-1-2:996fe7c6ac30c7b0",
      "capped_draws": 42,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 86,
      "draws": 42,
      "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": 77,
      "max_score": null,
      "measured_at": "2026-09-09T23:36:16Z",
      "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": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1623.6330641273657,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.80349713326343,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 103
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-6-sol:60281ce94ea88014",
      "capped_draws": 47,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 47,
      "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": 75,
      "max_score": null,
      "measured_at": "2026-09-10T11:07:22Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1614.9647465144133,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.92253340064839,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-5:fc52395a742e5644",
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 35,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-02T22:46:40Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1619.4173554954286,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.92973960121274,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:z-ai-glm-5-3:ebf51d85881ca5b8",
      "capped_draws": 33,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": "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": 50,
      "max_score": null,
      "measured_at": "2026-09-10T09:55:39Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1572.2266605384239,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.20578955238555,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 142,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-4-nano:65879fd5791a5546",
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 69,
      "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": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T20:41:31Z",
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1568.270065288822,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.81658368870027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 15.213976730923585,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 434,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:stealth-ox-alpha:03024ebf053d776c",
      "capped_draws": 132,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 217,
      "draws": 132,
      "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": 192,
      "max_score": null,
      "measured_at": "2026-09-10T09:59:50Z",
      "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": 434,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.3224253686287,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 40.48839717718149,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.44449391112387104,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:o3:9e4cf63e80682b9b",
      "capped_draws": 52,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 52,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:36:48Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.6927837582004,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.12700070176546,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 24
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:deepseek-deepseek-v4-flash:23183d74d990acfd",
      "capped_draws": 142,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 119,
      "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": "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": 72,
      "max_score": null,
      "measured_at": "2026-09-10T11:08:34Z",
      "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": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.4991366421373,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.52330614352358,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.44094811091393,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:google-gemini-3-1-flash-lite:a27c54e25bfb4de0",
      "capped_draws": 34,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 34,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:18:42Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.346762921776,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.74193137879505,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 148,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-6-terra:0fc18f792ad6d67d",
      "capped_draws": 38,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 74,
      "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-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": 89,
      "max_score": null,
      "measured_at": "2026-09-10T07:13:19Z",
      "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": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.9863882384893,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.57437059459893,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:nvidia-nemotron-3-ultra-550b-a55b:3bcb1a7b4e915226",
      "capped_draws": 52,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 52,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:39:02Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.6513922439997,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.57343311593441,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-4-mini:b89689b888a03e98",
      "capped_draws": 30,
      "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": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:18:57Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.99548468218,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.679683632220694,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:qwen-qwen3-7-max:1ec5e86937e80891",
      "capped_draws": 59,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 59,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 26,
      "max_score": null,
      "measured_at": "2026-08-05T01:39:17Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.143126017843,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.549311188071584,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 174,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:qwen-qwen3-8-flash:5a72b22afc48c9d2",
      "capped_draws": 89,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 87,
      "draws": 89,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-09-10T11:08:42Z",
      "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": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.7391422180938,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.30930546094415,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 265,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-4:91029345b4b373cd",
      "capped_draws": 173,
      "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": "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": 42,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:20Z",
      "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": 265,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.8641566204983,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.294233538337693,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:x-ai-grok-build-0-1:32469550859abedd",
      "capped_draws": 67,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 67,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 11,
      "max_score": null,
      "measured_at": "2026-08-04T23:07:13Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.5973144153943,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.19024732920317,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:minimax-minimax-m3:31a675d7727a5125",
      "capped_draws": 71,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 71,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 14,
      "max_score": null,
      "measured_at": "2026-08-05T01:31:56Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.3080306183583,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.97060306197978,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:qwen-qwen3-7-plus:d327d3640f27bd3b",
      "capped_draws": 74,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 74,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 16,
      "max_score": null,
      "measured_at": "2026-08-05T00:36:50Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.1673033832565,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.639092386388416,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 168,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:deepseek-deepseek-v4-pro-0813:e2a09b34905fa7a8",
      "capped_draws": 63,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 63,
      "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": 73,
      "max_score": null,
      "measured_at": "2026-09-10T07:15:16Z",
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.3061764466815,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.205666155415027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:claude-opus-4-8:0b9e44df31643ae8",
      "capped_draws": 63,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 63,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T23:29:48Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.7365888718184,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.00399105678296,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 147,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:thinkingmachines-inkling-small:76482ff3d2fed50c",
      "capped_draws": 111,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 68,
      "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": "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": 26,
      "max_score": null,
      "measured_at": "2026-09-10T07:15:50Z",
      "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": 147,
      "rating_method": "sequential_elo",
      "raw_elo": 1390.0220829331531,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.69344443534794,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 146,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:xiaomi-mimo-v2-5:9e3a1125fb872e8c",
      "capped_draws": 71,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 69,
      "draws": 71,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 54,
      "max_score": null,
      "measured_at": "2026-08-04T21:46:23Z",
      "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": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1397.0111643133864,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.07451833900503,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 14.473660794592899,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 330,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:moonshotai-kimi-k3:b25ef0843c2d972a",
      "capped_draws": 246,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 120,
      "draws": 246,
      "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": 67,
      "max_score": null,
      "measured_at": "2026-09-10T10:00:52Z",
      "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": 330,
      "rating_method": "sequential_elo",
      "raw_elo": 1372.3124171079544,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.06475884466223,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 174,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:google-gemini-3-8-flash:9fd2f22238c82925",
      "capped_draws": 118,
      "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": "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": 42,
      "max_score": null,
      "measured_at": "2026-09-10T07:24:04Z",
      "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": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1380.4579125856314,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.05501161815919,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:xiaomi-mimo-v2-5-pro:43c3a8c0c343b927",
      "capped_draws": 54,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 54,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 16,
      "max_score": null,
      "measured_at": "2026-08-04T08:41:53Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.7465030285916,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.56700348772194,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:qwen-qwen3-8-2-4t-a95b:a41a9f6e42ee2b8f",
      "capped_draws": 116,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "draws": 116,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-09-10T07:24:13Z",
      "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": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1377.2103402805674,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.541984464943933,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:claude-sonnet-5:765bc291b12a711e",
      "capped_draws": 157,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "draws": 157,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-09-10T11:08:22Z",
      "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": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1362.738639703256,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.738941337874866,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 142,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:openai-gpt-oss-120b:8fc70fdaca40b3e0",
      "capped_draws": 113,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 71,
      "draws": 113,
      "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": 19,
      "max_score": null,
      "measured_at": "2026-09-10T06:42:39Z",
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1366.298434717585,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.452641331825593,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 560,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:poolside-laguna-s-2-1:df6bf1faab8cda70",
      "capped_draws": 420,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 202,
      "draws": 420,
      "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": 112,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:54Z",
      "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": 560,
      "rating_method": "sequential_elo",
      "raw_elo": 1356.3901100732774,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.423065582541604,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5:2447de160165f34c",
      "capped_draws": 47,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 47,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:19:06Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1377.804308515359,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.220595380503127,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:inception-mercury-2-5-preview:6204f9f816b5cf60",
      "capped_draws": 117,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "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": "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": 6,
      "max_score": null,
      "measured_at": "2026-09-10T05:32:58Z",
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1361.0186166921785,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.802527118305367,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 551,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:meituan-longcat-2-0:26225fa06d2cccd9",
      "capped_draws": 193,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 195,
      "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": "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": 265,
      "max_score": null,
      "measured_at": "2026-09-10T09:56:44Z",
      "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": 551,
      "rating_method": "sequential_elo",
      "raw_elo": 1348.152961397977,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.64483119159765,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 126,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:z-ai-glm-5-3-flash:1cd9221832b4ca47",
      "capped_draws": 106,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 106,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-09-10T05:33:15Z",
      "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": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.5561479367261,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.64215239242983,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 273,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:thinkingmachines-inkling:3ab0a3aec8e194a6",
      "capped_draws": 184,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "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": "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": 65,
      "max_score": null,
      "measured_at": "2026-09-10T03:30:40Z",
      "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": 273,
      "rating_method": "sequential_elo",
      "raw_elo": 1346.4972068552136,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.482619661848684,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:cohere-north-mini-code:568529666a0f96d5",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 26,
      "draws": 60,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 16,
      "max_score": null,
      "measured_at": "2026-08-05T04:28:47Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1386.7126894336147,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.197441065976513,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 40.59014098717226,
      "unilateral_faults": null,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:meta-muse-glimmer-30b:05ba243db4d890c1",
      "capped_draws": 111,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": "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": 6,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:40Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1353.3431681451975,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.042987762318226,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 570,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:google-gemini-3-5-flash-lite:ada8852a63812f17",
      "capped_draws": 436,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 197,
      "draws": 436,
      "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": 107,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:31Z",
      "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": 570,
      "rating_method": "sequential_elo",
      "raw_elo": 1339.9247736299953,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.923559089613434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 176,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:z-ai-glm-5-2:ce87a33d1a10c901",
      "capped_draws": 138,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 88,
      "draws": 138,
      "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": 37,
      "max_score": null,
      "measured_at": "2026-09-10T11:10:18Z",
      "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": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.0107627204068,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.681783476260748,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 12.950820762170157,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-6-luna:56b3e8082c8d4caf",
      "capped_draws": 148,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 148,
      "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": 50,
      "max_score": null,
      "measured_at": "2026-09-10T09:56:44Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1337.1606904094851,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.298255599085287,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:ibm-granite-granite-4-2-8b:9c9c55a34daec5ca",
      "capped_draws": 105,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": "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": 19,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:08Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1318.9419863684932,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 21.86986836691461,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:google-gemini-3-5-flash:099e26902a6430db",
      "capped_draws": 75,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 75,
      "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": 48,
      "max_score": null,
      "measured_at": "2026-09-10T11:09:43Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1220.0518609352368,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.748374312932619,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:nex-agi-nex-n2-pro:ef6c9f2b08b0d606",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "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": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 51,
      "max_score": null,
      "measured_at": "2026-08-05T02:33:48Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1174.3876372219918,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 7.328898964258992,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 952,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-6-astra:24306100b4080f36",
      "capped_draws": 5,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "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": 75.3229753105928,
      "contributing_entrants": null,
      "distinct_rated_opponents": 41,
      "draws": 140,
      "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": "2026-09-10T10:58:46Z",
      "losses": 143,
      "max_score": 97.61905921533831,
      "measured_at": null,
      "min_score": 50.47588011557324,
      "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": 952,
      "rating_method": "sequential_elo",
      "raw_elo": 1860.3760146441941,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 75.3229753105928,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 8,
      "attempted_matches": 958,
      "canonical_public_row_identity": "publication-row.v1:baseline:claude-fable-5-1:82fc3985d63b4a72",
      "capped_draws": 1,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "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": 73.78797011506347,
      "contributing_entrants": null,
      "distinct_rated_opponents": 40,
      "draws": 123,
      "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": "2026-09-10T11:06:19Z",
      "losses": 161,
      "max_score": 89.2299699098686,
      "measured_at": null,
      "min_score": 44.553723611281114,
      "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": 952,
      "rating_method": "sequential_elo",
      "raw_elo": 1847.5349218158287,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 73.78797011506347,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 668
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1216,
      "canonical_public_row_identity": "publication-row.v1:baseline:claude-opus-5:e9ebdf808117b870",
      "capped_draws": 124,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 16
        },
        "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": 4.570124999999999
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 59.71965002282272,
      "contributing_entrants": null,
      "distinct_rated_opponents": 58,
      "draws": 248,
      "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": "2026-09-10T10:00:20Z",
      "losses": 219,
      "max_score": 81.06683069976471,
      "measured_at": null,
      "min_score": 36.957881306791684,
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1215,
      "rating_method": "sequential_elo",
      "raw_elo": 1722.6966437254782,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 57.75894702239247,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 748
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2356,
      "canonical_public_row_identity": "publication-row.v1:baseline:moonshotai-kimi-k3:5a54aec150052f73",
      "capped_draws": 203,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "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": 45.45362312867519,
      "contributing_entrants": null,
      "distinct_rated_opponents": 58,
      "draws": 654,
      "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": "2026-09-10T10:38:53Z",
      "losses": 769,
      "max_score": 89.21089685186311,
      "measured_at": null,
      "min_score": 11.367330732070096,
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2356,
      "rating_method": "sequential_elo",
      "raw_elo": 1553.5581213722062,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 45.45362312867519,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 933
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1096,
      "canonical_public_row_identity": "publication-row.v1:baseline:claude-fable-5:7f6b2a08dddc3940",
      "capped_draws": 30,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "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": 2.3088499999999996
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 44.77941641806791,
      "contributing_entrants": null,
      "distinct_rated_opponents": 42,
      "draws": 320,
      "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": "2026-09-10T11:07:47Z",
      "losses": 376,
      "max_score": 70.16961646402447,
      "measured_at": null,
      "min_score": 6.646568053595592,
      "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": 1095,
      "rating_method": "sequential_elo",
      "raw_elo": 1575.203509271904,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 44.77941641806791,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 399
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1819,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-6-sol:34bccf96d771d2e5",
      "capped_draws": 36,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "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": 44.64382299490942,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 416,
      "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": "2026-09-10T11:12:01Z",
      "losses": 581,
      "max_score": 71.00149057401816,
      "measured_at": null,
      "min_score": 13.272080636024716,
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1818,
      "rating_method": "sequential_elo",
      "raw_elo": 1554.1661383056335,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 44.64382299490942,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 821
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 470,
      "canonical_public_row_identity": "publication-row.v1:baseline:claude-opus-4-8:6a24675422272c49",
      "capped_draws": 17,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "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": 43.264323114773916,
      "contributing_entrants": null,
      "distinct_rated_opponents": 32,
      "draws": 130,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T03:47:33Z",
      "losses": 134,
      "max_score": 60.46952997771049,
      "measured_at": null,
      "min_score": 15.08783877564788,
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 470,
      "rating_method": "sequential_elo",
      "raw_elo": 1554.5581239066864,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 41.84387794956778,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 206
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 574,
      "canonical_public_row_identity": "publication-row.v1:baseline:claude-opus-4-5:11b2bcd9aa32f256",
      "capped_draws": 74,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "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": 41.44919981470518,
      "contributing_entrants": null,
      "distinct_rated_opponents": 34,
      "draws": 198,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T05:02:30Z",
      "losses": 173,
      "max_score": 57.33994820345935,
      "measured_at": null,
      "min_score": 16.904129430402378,
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 574,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.7089756027547,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 41.44919981470518,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 203
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1066,
      "canonical_public_row_identity": "publication-row.v1:baseline:google-gemini-3-8-flash:bf006bcd6ccb81c6",
      "capped_draws": 71,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "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": 0.2555334390339119
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.688636894322386,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 269,
      "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": "2026-09-10T11:11:52Z",
      "losses": 427,
      "max_score": 69.17178746172216,
      "measured_at": null,
      "min_score": 6.964348588339904,
      "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": 1065,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.5215652120276,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 40.688636894322386,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 369
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1022,
      "canonical_public_row_identity": "publication-row.v1:baseline:z-ai-glm-5-3-flash:1c774d2a8faa3025",
      "capped_draws": 173,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "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": 37.903624046046815,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 368,
      "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": "2026-09-10T11:08:42Z",
      "losses": 336,
      "max_score": 65.32971726850512,
      "measured_at": null,
      "min_score": 8.088342646823264,
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1022,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.56890944493,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 37.903624046046815,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 318
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 472,
      "canonical_public_row_identity": "publication-row.v1:baseline:qwen-qwen3-7-max:7378b9f3cb87014a",
      "capped_draws": 82,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "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": 0.18239874999999997
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.16034768625658,
      "contributing_entrants": null,
      "distinct_rated_opponents": 32,
      "draws": 161,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T05:33:39Z",
      "losses": 162,
      "max_score": 59.55002702144701,
      "measured_at": null,
      "min_score": 17.63292970387716,
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 472,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.1419776261966,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 37.87464337993543,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 149
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2227,
      "canonical_public_row_identity": "publication-row.v1:baseline:x-ai-grok-4-5:0d820700fd8c1f0b",
      "capped_draws": 200,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "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": 37.20786073928545,
      "contributing_entrants": null,
      "distinct_rated_opponents": 58,
      "draws": 696,
      "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": "2026-09-10T11:11:37Z",
      "losses": 759,
      "max_score": 69.67529740665044,
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2227,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.3095894734206,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 37.20786073928545,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 772
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1728,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-4:86f20e721b83e093",
      "capped_draws": 176,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "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": 37.161284828496534,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 582,
      "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": "2026-09-10T11:11:29Z",
      "losses": 616,
      "max_score": 64.11149296941215,
      "measured_at": null,
      "min_score": 8.247425935777672,
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1728,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.3571984020155,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 37.161284828496534,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 530
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 572,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-4-1:fccd725c87f1cbd8",
      "capped_draws": 71,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 11
        },
        "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": 0.45756399999999997
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 35.80056693008479,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 196,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T05:41:31Z",
      "losses": 198,
      "max_score": 55.88308492443146,
      "measured_at": null,
      "min_score": 11.682283349084813,
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 571,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.7983515817293,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 35.80056693008479,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 177
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1002,
      "canonical_public_row_identity": "publication-row.v1:baseline:qwen-qwen3-8-2-4t-a95b:2caf8bc899f551f3",
      "capped_draws": 71,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 9
        },
        "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": 35.210841176918336,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 281,
      "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": "2026-09-10T10:39:03Z",
      "losses": 365,
      "max_score": 64.6317689865653,
      "measured_at": null,
      "min_score": 11.392747323534184,
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1001,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.6088649070266,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 35.210841176918336,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 355
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1002,
      "canonical_public_row_identity": "publication-row.v1:baseline:z-ai-glm-5-3:d95da7acd9780380",
      "capped_draws": 114,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "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": 35.13669356616318,
      "contributing_entrants": null,
      "distinct_rated_opponents": 42,
      "draws": 348,
      "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": "2026-09-10T11:09:46Z",
      "losses": 388,
      "max_score": 61.34368150573174,
      "measured_at": null,
      "min_score": 10.263403044539475,
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1000,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.325274967785,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 35.13669356616318,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 264
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 454,
      "canonical_public_row_identity": "publication-row.v1:baseline:minimax-minimax-m3:ce3665e0f9c1f1b1",
      "capped_draws": 23,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "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": 36.383144914207264,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 101,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T04:33:21Z",
      "losses": 180,
      "max_score": 46.440218311437484,
      "measured_at": null,
      "min_score": 12.190471042456242,
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 454,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.4791809138806,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 33.85833144657712,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 173
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 534,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-5:8d8c6268a221d9ee",
      "capped_draws": 145,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "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": 34.83562498827739,
      "contributing_entrants": null,
      "distinct_rated_opponents": 34,
      "draws": 275,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "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": "2026-08-05T05:23:57Z",
      "losses": 149,
      "max_score": 49.787345255628644,
      "measured_at": null,
      "min_score": 13.936024036303673,
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 534,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.652701429713,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 33.69190906880573,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1090,
      "canonical_public_row_identity": "publication-row.v1:baseline:tencent-hy4-preview:9b637fbe1929d4b6",
      "capped_draws": 150,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "evidence_basis": "Provider-reported",
        "max": 0.028804516000000002,
        "mean": 0.015939765625,
        "median": 0.0150484685,
        "min": 0.009391185,
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.12751812499999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 33.54804237444562,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 404,
      "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": "2026-09-10T11:11:38Z",
      "losses": 341,
      "max_score": 48.348251895031375,
      "measured_at": null,
      "min_score": 7.401997425923536,
      "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": 1090,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.3365216218722,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 33.54804237444562,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 345
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1120,
      "canonical_public_row_identity": "publication-row.v1:baseline:qwen-qwen3-8-max:3a653d034173d2f2",
      "capped_draws": 143,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "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": 0.9576840000000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 33.52240330497203,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 423,
      "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": "2026-09-10T10:49:44Z",
      "losses": 375,
      "max_score": 88.76990902930297,
      "measured_at": null,
      "min_score": 6.07109411954341,
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1120,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.2548859983672,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 33.52240330497203,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 8,
      "attempted_matches": 1728,
      "canonical_public_row_identity": "publication-row.v1:baseline:meta-muse-spark-1-2:772fc6bb6f83c6c9",
      "capped_draws": 107,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "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": 33.482296955476336,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 416,
      "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": "2026-09-10T11:08:49Z",
      "losses": 772,
      "max_score": 53.37102488938938,
      "measured_at": null,
      "min_score": 3.906687867060584,
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1728,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.0124587833386,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 33.482296955476336,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 540
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 1219,
      "canonical_public_row_identity": "publication-row.v1:baseline:poolside-laguna-s-2-1:834cbfa8b37e299a",
      "capped_draws": 203,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 33
        },
        "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": 34.67716153953121,
      "contributing_entrants": null,
      "distinct_rated_opponents": 60,
      "draws": 429,
      "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": "2026-09-10T08:23:32Z",
      "losses": 408,
      "max_score": 54.10090278289114,
      "measured_at": null,
      "min_score": 9.449979970240136,
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1211,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.3951550877723,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 33.36620733645767,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 374
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": 4003,
      "canonical_public_row_identity": "publication-row.v1:baseline:google-gemini-3-5-flash-lite:d8ea2a1333ff0452",
      "capped_draws": 590,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 34
        },
        "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": 33.8042060754052,
      "contributing_entrants": null,
      "distinct_rated_opponents": 58,
      "draws": 1362,
      "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": "2026-09-10T11:12:00Z",
      "losses": 1532,
      "max_score": 65.89914757897805,
      "measured_at": null,
      "min_score": 9.623986038775216,
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3997,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.6909229985479,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 33.26316420086277,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1103
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1698,
      "canonical_public_row_identity": "publication-row.v1:baseline:claude-sonnet-5:5d48f6168d64e7fe",
      "capped_draws": 150,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "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": 0.49337000000000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 33.01117377347347,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 509,
      "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": "2026-09-10T10:49:31Z",
      "losses": 658,
      "max_score": 44.742957151306456,
      "measured_at": null,
      "min_score": 11.223439055353664,
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1698,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.8756883438432,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 33.01117377347347,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 531
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 380,
      "canonical_public_row_identity": "publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:8548115fcae6ae84",
      "capped_draws": 75,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "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": 34.63718896016983,
      "contributing_entrants": null,
      "distinct_rated_opponents": 30,
      "draws": 129,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "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": "2026-07-31T03:28:04Z",
      "losses": 150,
      "max_score": 57.3153424952665,
      "measured_at": null,
      "min_score": 24.0096350455345,
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 380,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.0221765297592,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 32.52793710179262,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 12,
      "attempted_matches": 860,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-4-nano:2d8b3620ce9c297f",
      "capped_draws": 118,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 27
        },
        "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": 34.89630279530046,
      "contributing_entrants": null,
      "distinct_rated_opponents": 34,
      "draws": 264,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "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": "2026-08-05T05:41:31Z",
      "losses": 336,
      "max_score": 51.6471832448803,
      "measured_at": null,
      "min_score": 12.179369637744257,
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 860,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.363933510578,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 32.47466894600478,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 260
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1054,
      "canonical_public_row_identity": "publication-row.v1:baseline:x-ai-grok-4-6:f1d4c61e0708aeae",
      "capped_draws": 119,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "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": 32.338738807789284,
      "contributing_entrants": null,
      "distinct_rated_opponents": 42,
      "draws": 438,
      "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": "2026-09-10T11:06:41Z",
      "losses": 393,
      "max_score": 54.57488465434671,
      "measured_at": null,
      "min_score": 9.318441010342715,
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1054,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.0219042816693,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 32.338738807789284,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 223
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 1828,
      "canonical_public_row_identity": "publication-row.v1:baseline:z-ai-glm-5-2:51bd53334ebd6ddf",
      "capped_draws": 221,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 37
        },
        "evidence_basis": "Provider-reported",
        "max": 0.03729904666666666,
        "mean": 0.023546225995833333,
        "median": 0.024102434966666662,
        "min": 0.013816857666666668,
        "recorded_attempt_count": 37,
        "run_count": 24,
        "total": 0.5651094239
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 31.90027122341541,
      "contributing_entrants": null,
      "distinct_rated_opponents": 63,
      "draws": 668,
      "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": "2026-09-10T11:06:45Z",
      "losses": 640,
      "max_score": 50.75736719314747,
      "measured_at": null,
      "min_score": 10.165756558589774,
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1828,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.6583595116074,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 31.90027122341541,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 520
    },
    {
      "admitted_plugins": 28,
      "attempted_matches": 3758,
      "canonical_public_row_identity": "publication-row.v1:baseline:stealth-ox-alpha:2a6c37bfc1ea9a10",
      "capped_draws": 403,
      "codegen_cost_usd": {
        "admitted_cell_count": 28,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 42
        },
        "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": 32.180212780950036,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 1517,
      "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": "2026-09-10T11:06:20Z",
      "losses": 1250,
      "max_score": 49.214171810132676,
      "measured_at": null,
      "min_score": 10.84501570624497,
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3751,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.2866553587492,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 31.629920879680903,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 984
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 818,
      "canonical_public_row_identity": "publication-row.v1:baseline:deepseek-deepseek-v4-pro:ff3e59d607a4ac18",
      "capped_draws": 172,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "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": 33.97145389410562,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 334,
      "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": "2026-09-10T11:09:42Z",
      "losses": 259,
      "max_score": 49.08988614590849,
      "measured_at": null,
      "min_score": 21.38393789540447,
      "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": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 818,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.2335721457046,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 31.614000064617635,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 7,
      "attempted_matches": 963,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-6-terra:9663b021bc677328",
      "capped_draws": 153,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "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": 32.581399173722424,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 401,
      "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": "2026-09-10T11:12:01Z",
      "losses": 306,
      "max_score": 47.20969665141295,
      "measured_at": null,
      "min_score": 9.955451026536553,
      "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": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 963,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.5765046902507,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 31.51169352250512,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 256
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": 1110,
      "canonical_public_row_identity": "publication-row.v1:baseline:xiaomi-mimo-v2-5:a7d613e15ebacf2f",
      "capped_draws": 142,
      "codegen_cost_usd": {
        "admitted_cell_count": 17,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 37
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 7,
        "max": 0.005169185000000001,
        "mean": 0.002871050658333333,
        "median": 0.0023354879666666667,
        "min": 0.0016912200000000002,
        "recorded_attempt_count": 37,
        "run_count": 24,
        "total": 0.06890521579999999
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 34.497841045473734,
      "contributing_entrants": null,
      "distinct_rated_opponents": 34,
      "draws": 297,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T05:41:45Z",
      "losses": 430,
      "max_score": 49.95050528925342,
      "measured_at": null,
      "min_score": 10.940010823479835,
      "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": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1108,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.1291738056846,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 31.413049046831127,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 381
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 404,
      "canonical_public_row_identity": "publication-row.v1:baseline:tencent-hy3-preview:e682bc091589ac52",
      "capped_draws": 79,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "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": 0.010139174
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 33.64300657853923,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 178,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "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": "2026-08-05T05:08:37Z",
      "losses": 110,
      "max_score": 64.07635846709539,
      "measured_at": null,
      "min_score": 7.405950095136704,
      "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": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 404,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.7454238739876,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 31.308345396792507,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 116
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 4456,
      "canonical_public_row_identity": "publication-row.v1:baseline:google-gemini-3-6-flash:497c5e32f5a0da50",
      "capped_draws": 596,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 29
        },
        "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": 31.213596289340646,
      "contributing_entrants": null,
      "distinct_rated_opponents": 58,
      "draws": 1589,
      "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": "2026-09-10T11:11:14Z",
      "losses": 1675,
      "max_score": 49.274306768900956,
      "measured_at": null,
      "min_score": 8.821204616548417,
      "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": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 4451,
      "rating_method": "sequential_elo",
      "raw_elo": 1396.470667662523,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 31.213596289340646,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1187
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 776,
      "canonical_public_row_identity": "publication-row.v1:baseline:deepseek-deepseek-v4-pro-0813:62f039a975dbbc18",
      "capped_draws": 150,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "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": 33.372176280108306,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 294,
      "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": "2026-09-10T11:09:23Z",
      "losses": 297,
      "max_score": 58.27831291867289,
      "measured_at": null,
      "min_score": 25.054798702264524,
      "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": 776,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.4146475615432,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 31.05630940508062,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 185
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1079,
      "canonical_public_row_identity": "publication-row.v1:baseline:meta-muse-spark-1-3:b665bb24258fc911",
      "capped_draws": 164,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "evidence_basis": "Provider-reported",
        "max": 0.043892749999999994,
        "mean": 0.023888718750000003,
        "median": 0.020423875,
        "min": 0.017614,
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.19110974999999997
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 30.330821034598397,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 388,
      "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": "2026-09-10T11:11:12Z",
      "losses": 345,
      "max_score": 45.686593077752605,
      "measured_at": null,
      "min_score": 10.355871463342384,
      "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": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1071,
      "rating_method": "sequential_elo",
      "raw_elo": 1401.131294871489,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 30.330821034598397,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 338
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 980,
      "canonical_public_row_identity": "publication-row.v1:baseline:thinkingmachines-inkling:70a9ac993f011430",
      "capped_draws": 87,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 39
        },
        "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": 31.709014387195165,
      "contributing_entrants": null,
      "distinct_rated_opponents": 34,
      "draws": 291,
      "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": "2026-08-05T05:16:45Z",
      "losses": 403,
      "max_score": 60.57535339573391,
      "measured_at": null,
      "min_score": 12.336409573070739,
      "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": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 980,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.1747761848974,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 29.508562866062203,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 286
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1178,
      "canonical_public_row_identity": "publication-row.v1:baseline:meituan-longcat-2-0:8409ccd1edce8105",
      "capped_draws": 236,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 38
        },
        "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": 0.21404720400000005
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 30.345518662237996,
      "contributing_entrants": null,
      "distinct_rated_opponents": 34,
      "draws": 415,
      "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": "2026-08-05T05:24:42Z",
      "losses": 444,
      "max_score": 44.89316223345493,
      "measured_at": null,
      "min_score": 8.990579277651428,
      "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": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1174,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.294317219309,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 29.3492209701396,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 315
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 560,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-4-mini:8b748b4207b1c84c",
      "capped_draws": 85,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "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": 0.14705250000000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 28.42341314043818,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 250,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": "2026-08-05T05:24:08Z",
      "losses": 205,
      "max_score": 39.92088394835182,
      "measured_at": null,
      "min_score": 12.418449045966476,
      "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": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 556,
      "rating_method": "sequential_elo",
      "raw_elo": 1383.8728599981719,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 28.42341314043818,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 101
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1064,
      "canonical_public_row_identity": "publication-row.v1:baseline:qwen-qwen3-8-flash:2ed602cefebb326c",
      "capped_draws": 167,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "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": 26.70950374619811,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 435,
      "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": "2026-09-10T11:08:14Z",
      "losses": 420,
      "max_score": 52.04746013492715,
      "measured_at": null,
      "min_score": 8.345895178371906,
      "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": 1064,
      "rating_method": "sequential_elo",
      "raw_elo": 1357.1212983556989,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 26.70950374619811,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 209
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 926,
      "canonical_public_row_identity": "publication-row.v1:baseline:deepseek-deepseek-v4-flash:b05f493f9c8d196b",
      "capped_draws": 120,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "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": 26.614508029189267,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 283,
      "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": "2026-09-10T11:06:06Z",
      "losses": 371,
      "max_score": 48.009788801136246,
      "measured_at": null,
      "min_score": 8.085742846285687,
      "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": 926,
      "rating_method": "sequential_elo",
      "raw_elo": 1341.127056397135,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 25.740706094183555,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 272
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 432,
      "canonical_public_row_identity": "publication-row.v1:baseline:qwen-qwen3-7-plus:c57dfba2bd8782fc",
      "capped_draws": 22,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "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": 27.57407026128659,
      "contributing_entrants": null,
      "distinct_rated_opponents": 32,
      "draws": 143,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T03:19:33Z",
      "losses": 189,
      "max_score": 50.37567398128637,
      "measured_at": null,
      "min_score": 14.181701766649182,
      "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": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 430,
      "rating_method": "sequential_elo",
      "raw_elo": 1368.1228288641923,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 24.9159851357772,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 98
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 750,
      "canonical_public_row_identity": "publication-row.v1:baseline:meta-muse-glimmer-30b:5f799292ad06c854",
      "capped_draws": 162,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "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": 26.077506622187926,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 282,
      "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": "2026-09-10T11:05:42Z",
      "losses": 301,
      "max_score": 37.00463002835304,
      "measured_at": null,
      "min_score": 6.990073492948425,
      "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": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 750,
      "rating_method": "sequential_elo",
      "raw_elo": 1318.3136365028786,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 24.267854375875263,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 167
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 750,
      "canonical_public_row_identity": "publication-row.v1:baseline:openai-gpt-oss-120b:e4864d083f4798c2",
      "capped_draws": 143,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "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": 25.417909395473753,
      "contributing_entrants": null,
      "distinct_rated_opponents": 42,
      "draws": 292,
      "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": "2026-09-10T11:05:48Z",
      "losses": 268,
      "max_score": 40.640073310441565,
      "measured_at": null,
      "min_score": 9.761584645888398,
      "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": 44,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 750,
      "rating_method": "sequential_elo",
      "raw_elo": 1341.9142700886227,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 23.654029991644784,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 190
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 864,
      "canonical_public_row_identity": "publication-row.v1:baseline:bytedance-seed-seed-2-0-code:95b26b11b0986534",
      "capped_draws": 162,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "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": 0.16760899999999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 23.90857395896249,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 289,
      "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": "2026-09-10T11:06:39Z",
      "losses": 398,
      "max_score": 34.82242746606155,
      "measured_at": null,
      "min_score": 14.961257423631709,
      "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": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 858,
      "rating_method": "sequential_elo",
      "raw_elo": 1276.554271400966,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 23.12361268274216,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 171
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 642,
      "canonical_public_row_identity": "publication-row.v1:baseline:inception-mercury-2-5-preview:ae4030f1f9433705",
      "capped_draws": 11,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "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": 23.962159689024865,
      "contributing_entrants": null,
      "distinct_rated_opponents": 42,
      "draws": 258,
      "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": "2026-09-10T10:05:55Z",
      "losses": 217,
      "max_score": 39.11032563550241,
      "measured_at": null,
      "min_score": 11.73718454940338,
      "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": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 641,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.8631378590524,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 21.305707597528798,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 166
    },
    {
      "admitted_plugins": 10,
      "attempted_matches": 1068,
      "canonical_public_row_identity": "publication-row.v1:baseline:inclusionai-ling-3-0-flash:fde230dc0f90d703",
      "capped_draws": 289,
      "codegen_cost_usd": {
        "admitted_cell_count": 10,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 40
        },
        "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": 22.86688675022906,
      "contributing_entrants": null,
      "distinct_rated_opponents": 34,
      "draws": 533,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T05:41:59Z",
      "losses": 359,
      "max_score": 37.1347934270453,
      "measured_at": null,
      "min_score": 7.0150208382150785,
      "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": 47,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1066,
      "rating_method": "sequential_elo",
      "raw_elo": 1360.6475316318747,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 20.331856939812095,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 174
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1116,
      "canonical_public_row_identity": "publication-row.v1:baseline:thinkingmachines-inkling-small:2a1c609d5f09a424",
      "capped_draws": 166,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "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": 20.689010458032868,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 482,
      "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": "2026-09-10T11:11:12Z",
      "losses": 442,
      "max_score": 31.934103720162618,
      "measured_at": null,
      "min_score": 0.0,
      "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": 48,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1115,
      "rating_method": "sequential_elo",
      "raw_elo": 1273.991138220205,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 20.08868868428344,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 191
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 290,
      "canonical_public_row_identity": "publication-row.v1:baseline:google-gemini-3-1-flash-lite:890697e687a48241",
      "capped_draws": 19,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "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": 21.823970921280427,
      "contributing_entrants": null,
      "distinct_rated_opponents": 30,
      "draws": 67,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "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": "2026-07-31T03:34:49Z",
      "losses": 167,
      "max_score": 39.06289260104517,
      "measured_at": null,
      "min_score": 14.474268235287061,
      "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": 49,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 290,
      "rating_method": "sequential_elo",
      "raw_elo": 1270.8645282982493,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 19.404559067300582,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1604,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-6-luna:1c8c41335b2357b1",
      "capped_draws": 104,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "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": 16.090509598812808,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 526,
      "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": "2026-09-10T11:01:22Z",
      "losses": 845,
      "max_score": 24.54821424333988,
      "measured_at": null,
      "min_score": 0.0,
      "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": 50,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1604,
      "rating_method": "sequential_elo",
      "raw_elo": 1228.9818249502457,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 16.090509598812808,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 233
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 438,
      "canonical_public_row_identity": "publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:8ba9ac7e5b78b94d",
      "capped_draws": 30,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 7,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.1311545862,
        "mean": 0.02955606902857143,
        "median": 0.0063034062,
        "min": 0.0057139812,
        "recorded_attempt_count": 10,
        "run_count": 7,
        "total": 0.2068924832
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 37.32543758140332,
      "contributing_entrants": null,
      "distinct_rated_opponents": 31,
      "draws": 104,
      "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": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 0.5714285714285714,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_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": "2026-08-05T04:19:05Z",
      "losses": 166,
      "max_score": 53.03980999081365,
      "measured_at": null,
      "min_score": 16.473094673491183,
      "model_code_failure_rate": 0.14285714285714285,
      "model_code_failures": 1,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": 0.8571428571428571,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 438,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.0654512452504,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 0.2857142857142857,
      "results_cut_id": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 35.91436651599566,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 168
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-4-1-nano:e6370d2aaad0f23a",
      "capped_draws": 65,
      "codegen_cost_usd": {
        "admitted_cell_count": 1,
        "cell_count": 1,
        "cost_basis_counts": {
          "estimated": 1,
          "local_standard_estimate": 1
        },
        "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": 35.18099307381629,
      "contributing_entrants": null,
      "distinct_rated_opponents": 45,
      "draws": 65,
      "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": "2026-09-10T04:08:50Z",
      "losses": 103,
      "max_score": 35.18099307381629,
      "measured_at": null,
      "min_score": 35.18099307381629,
      "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": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 1388.89236890581,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 35.18099307381629,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 474,
      "canonical_public_row_identity": "publication-row.v1:baseline:google-gemma-4-31b-it:a05cbdb73d0f0757",
      "capped_draws": 85,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 7,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "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": 32.242665330503485,
      "contributing_entrants": null,
      "distinct_rated_opponents": 34,
      "draws": 142,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T03:48:11Z",
      "losses": 198,
      "max_score": 47.537908439761935,
      "measured_at": null,
      "min_score": 24.766615824644276,
      "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": 472,
      "rating_method": "sequential_elo",
      "raw_elo": 1374.7432089327137,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 31.023746141136392,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 132
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 1110,
      "canonical_public_row_identity": "publication-row.v1:baseline:stepfun-step-3-7-flash:283efeb922617cca",
      "capped_draws": 192,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 20
        },
        "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": 0.19924718000000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 35.63407345020555,
      "contributing_entrants": null,
      "distinct_rated_opponents": 55,
      "draws": 216,
      "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": "2026-09-10T11:06:38Z",
      "losses": 519,
      "max_score": 47.765690377579354,
      "measured_at": null,
      "min_score": 20.829015374383967,
      "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": 1106,
      "rating_method": "sequential_elo",
      "raw_elo": 1357.5958608523906,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 29.96456462516541,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 371
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 476,
      "canonical_public_row_identity": "publication-row.v1:baseline:nex-agi-nex-n2-pro:66b75a517d8692bb",
      "capped_draws": 77,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 36
        },
        "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": 34.363072647101255,
      "contributing_entrants": null,
      "distinct_rated_opponents": 32,
      "draws": 222,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T04:41:06Z",
      "losses": 137,
      "max_score": 60.77934776395481,
      "measured_at": null,
      "min_score": 12.252825466946847,
      "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": 476,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.5851529093154,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 27.947084277846592,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 117
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1022,
      "canonical_public_row_identity": "publication-row.v1:baseline:google-gemini-3-5-flash:8f1504913d7602c4",
      "capped_draws": 151,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 11,
          "provider_reported": 14
        },
        "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": 23.68539356485576,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 384,
      "eligibility_flag": false,
      "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": "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": "2026-09-10T11:08:37Z",
      "losses": 384,
      "max_score": 52.643022639184814,
      "measured_at": null,
      "min_score": 8.860426297576485,
      "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": 1022,
      "rating_method": "sequential_elo",
      "raw_elo": 1335.8563162445548,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 23.68539356485576,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 254
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 1110,
      "canonical_public_row_identity": "publication-row.v1:baseline:o3:647217df3b12bb67",
      "capped_draws": 289,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "estimated": 8,
          "local_standard_estimate": 13
        },
        "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": 26.102373200502253,
      "contributing_entrants": null,
      "distinct_rated_opponents": 57,
      "draws": 329,
      "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": "2026-09-10T10:03:47Z",
      "losses": 564,
      "max_score": 44.781096360775045,
      "measured_at": null,
      "min_score": 13.652811210043236,
      "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": 1110,
      "rating_method": "sequential_elo",
      "raw_elo": 1254.6346491602558,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 21.94939205391697,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 217
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 428,
      "canonical_public_row_identity": "publication-row.v1:baseline:cohere-north-mini-code:bf20f7708e3f608c",
      "capped_draws": 156,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 30
        },
        "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": 29.334470894205833,
      "contributing_entrants": null,
      "distinct_rated_opponents": 34,
      "draws": 156,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T05:09:16Z",
      "losses": 198,
      "max_score": 33.07868627119113,
      "measured_at": null,
      "min_score": 26.207095835838984,
      "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": 424,
      "rating_method": "sequential_elo",
      "raw_elo": 1334.5884303676582,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 21.93263264971003,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 70
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-row.v1:baseline:qwen-qwen3-8-27b:4712c07305d96aee",
      "capped_draws": 101,
      "codegen_cost_usd": {
        "admitted_cell_count": 3,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "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": 0.17566727999999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 23.705963362379308,
      "contributing_entrants": null,
      "distinct_rated_opponents": 42,
      "draws": 180,
      "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": "2026-09-10T11:06:09Z",
      "losses": 52,
      "max_score": 24.392761540116325,
      "measured_at": null,
      "min_score": 23.019165184642294,
      "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": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.1571286454732,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 18.550918857121076,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 22,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-6-astra:24306100b4080f36",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "draws": 5,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-09-10T10:09:34Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1993.4538122220206,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 83.85408145856084,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 100
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01: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": 59,
      "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": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-09-10T10:15:28Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1915.473139954479,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 77.44093849930564,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 203,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-6-sol:34bccf96d771d2e5",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "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-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": 61,
      "max_score": null,
      "measured_at": "2026-09-10T11:12:01Z",
      "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": 203,
      "rating_method": "sequential_elo",
      "raw_elo": 1828.5102740039317,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 71.00149057401816,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 204,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-4:86f20e721b83e093",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "draws": 15,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:29Z",
      "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": 204,
      "rating_method": "sequential_elo",
      "raw_elo": 1744.6628933313261,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 64.11149296941215,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:tencent-hy3-preview:e682bc091589ac52",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 12,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:08:37Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1765.1662409309436,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 64.07635846709539,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 184,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:claude-opus-5:e9ebdf808117b870",
      "capped_draws": 84,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 88,
      "draws": 84,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-08-05T05:15:42Z",
      "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": 183,
      "rating_method": "sequential_elo",
      "raw_elo": 1682.921562770389,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 57.90922869975661,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.265465154150444,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:qwen-qwen3-7-max:7378b9f3cb87014a",
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 21,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 12,
      "max_score": null,
      "measured_at": "2026-07-30T23:26:21Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1655.1143223765005,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.08434421637588,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-4-1:fccd725c87f1cbd8",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "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-4.1",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 31,
      "max_score": null,
      "measured_at": "2026-08-05T04:19:05Z",
      "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": 81,
      "rating_method": "sequential_elo",
      "raw_elo": 1635.2135372709856,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.77515864460839,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.465763037423269,
      "unilateral_faults": 1,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:claude-fable-5:7f6b2a08dddc3940",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 15,
      "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": 56,
      "max_score": null,
      "measured_at": "2026-09-10T11:07:47Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1602.7025644270188,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 51.74366231437673,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:claude-opus-4-8:6a24675422272c49",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 17,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 15,
      "max_score": null,
      "measured_at": "2026-07-31T01:07:22Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1600.772685219599,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.49524544599616,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 32
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 156,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-4-nano:2d8b3620ce9c297f",
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 76,
      "draws": 49,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:01:18Z",
      "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": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1580.3713321653136,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.18855338448374,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 12.626594026364666,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:z-ai-glm-5-3:d95da7acd9780380",
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 21,
      "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": 60,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:19Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.9304941065209,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.63728121007812,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:google-gemma-4-31b-it:a05cbdb73d0f0757",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 30,
      "max_score": null,
      "measured_at": "2026-08-05T03:13:53Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1555.8128707841634,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.537908439761935,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:x-ai-grok-4-6:f1d4c61e0708aeae",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "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": "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": 67,
      "max_score": null,
      "measured_at": "2026-09-10T04:07:50Z",
      "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": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1544.2101064830151,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.0047308381856,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 142,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:google-gemini-3-8-flash:bf006bcd6ccb81c6",
      "capped_draws": 52,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 71,
      "draws": 52,
      "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": 61,
      "max_score": null,
      "measured_at": "2026-09-10T03:21:48Z",
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.7506367849912,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.88837008118324,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:8548115fcae6ae84",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 12,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T03:24:08Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1551.903907212254,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.34461449749834,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:minimax-minimax-m3:ce3665e0f9c1f1b1",
      "capped_draws": 20,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "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": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 32,
      "max_score": null,
      "measured_at": "2026-08-05T03:20:28Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.7263032874123,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.149209979529324,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 340,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:x-ai-grok-4-5:0d820700fd8c1f0b",
      "capped_draws": 200,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 123,
      "draws": 200,
      "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": 90,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:37Z",
      "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": 340,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.9079406908675,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.3213471472622,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:xiaomi-mimo-v2-5:a7d613e15ebacf2f",
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 120,
      "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": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-08-05T01:58:44Z",
      "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": 1526.400529711971,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.87218943706828,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 10.769176094020247,
      "unilateral_faults": 0,
      "wins": 93
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 339,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:moonshotai-kimi-k3:5a54aec150052f73",
      "capped_draws": 198,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 121,
      "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": "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": 85,
      "max_score": null,
      "measured_at": "2026-09-10T10:00:57Z",
      "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": 339,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.2302043286434,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.276110266794404,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-5:8d8c6268a221d9ee",
      "capped_draws": 76,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 76,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:09:23Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.9554170592792,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.211695324514714,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 192,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:poolside-laguna-s-2-1:834cbfa8b37e299a",
      "capped_draws": 43,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 92,
      "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": "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": 78,
      "max_score": null,
      "measured_at": "2026-08-05T05:02:20Z",
      "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": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.9064973950458,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.92223550931248,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.090352872155288,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 144,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:tencent-hy4-preview:9b637fbe1929d4b6",
      "capped_draws": 30,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "draws": 30,
      "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": 46,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:38Z",
      "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": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.93570480965,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.97510007604222,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 155,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-6-terra:9663b021bc677328",
      "capped_draws": 60,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 78,
      "draws": 60,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-09-10T11:12:01Z",
      "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": 155,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.2113320692047,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.780001569180335,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 146,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:openai-gpt-oss-120b:e4864d083f4798c2",
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "draws": 29,
      "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": 51,
      "max_score": null,
      "measured_at": "2026-09-10T07:20:06Z",
      "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": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.316176854037,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 40.640073310441565,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:claude-sonnet-5:5d48f6168d64e7fe",
      "capped_draws": 41,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "draws": 41,
      "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": 97,
      "max_score": null,
      "measured_at": "2026-09-10T06:33:43Z",
      "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": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.585426437345,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 40.38863436219846,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:claude-opus-4-5:11b2bcd9aa32f256",
      "capped_draws": 62,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "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-opus-4-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 20,
      "max_score": null,
      "measured_at": "2026-08-05T05:02:30Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.0431859406906,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 38.72217677162721,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 12
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 130,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:google-gemini-3-5-flash:8f1504913d7602c4",
      "capped_draws": 36,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 65,
      "draws": 36,
      "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": 37,
      "max_score": null,
      "measured_at": "2026-09-10T04:54:04Z",
      "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": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.3260253195192,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.2725961852945,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 264,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:inclusionai-ling-3-0-flash:fde230dc0f90d703",
      "capped_draws": 83,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 98,
      "draws": 83,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 97,
      "max_score": null,
      "measured_at": "2026-08-05T05:09:16Z",
      "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": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.3866478960922,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.1347934270453,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 128,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:meta-muse-glimmer-30b:5f799292ad06c854",
      "capped_draws": 43,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "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": "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": 40,
      "max_score": null,
      "measured_at": "2026-09-10T04:12:37Z",
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.3375622947487,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.00463002835304,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:8ba9ac7e5b78b94d",
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 26,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 45,
      "max_score": null,
      "measured_at": "2026-08-05T04:19:05Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.1690382660745,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 36.13581747923515,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:z-ai-glm-5-3-flash:1c774d2a8faa3025",
      "capped_draws": 86,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 68,
      "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": "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": 31,
      "max_score": null,
      "measured_at": "2026-09-10T04:07:20Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.9308922376556,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.9878998561934,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 573,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:google-gemini-3-5-flash-lite:d8ea2a1333ff0452",
      "capped_draws": 133,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 206,
      "draws": 133,
      "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": 239,
      "max_score": null,
      "measured_at": "2026-09-10T11:12:00Z",
      "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": 573,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.6675927319038,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.52053358030793,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 201
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-4-mini:8b748b4207b1c84c",
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 35,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:15:42Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.332536316064,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.304603292582,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-4-1-nano:e6370d2aaad0f23a",
      "capped_draws": 65,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 65,
      "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": 103,
      "max_score": null,
      "measured_at": "2026-09-10T04:08:50Z",
      "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": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 1388.89236890581,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.18099307381629,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 3,
      "attempted_matches": 400,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:stealth-ox-alpha:2a6c37bfc1ea9a10",
      "capped_draws": 120,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 200,
      "draws": 120,
      "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": 154,
      "max_score": null,
      "measured_at": "2026-09-10T10:10:04Z",
      "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": 400,
      "rating_method": "sequential_elo",
      "raw_elo": 1394.9933919244042,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.80493220290756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.5681818181818196,
      "unilateral_faults": 0,
      "wins": 126
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 210,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:meituan-longcat-2-0:8409ccd1edce8105",
      "capped_draws": 71,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 99,
      "draws": 71,
      "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": 80,
      "max_score": null,
      "measured_at": "2026-08-05T05:02:36Z",
      "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": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1390.4482752690915,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.08227841090624,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.828889084636114,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:qwen-qwen3-8-flash:2ed602cefebb326c",
      "capped_draws": 43,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": "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": 37,
      "max_score": null,
      "measured_at": "2026-09-10T11:08:14Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1386.0107501750101,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.92289285331455,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:deepseek-deepseek-v4-pro:ff3e59d607a4ac18",
      "capped_draws": 46,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": "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": 53,
      "max_score": null,
      "measured_at": "2026-09-10T11:09:42Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1356.9101246436917,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.55406582718129,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 202,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:meta-muse-spark-1-2:772fc6bb6f83c6c9",
      "capped_draws": 98,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "draws": 98,
      "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": 68,
      "max_score": null,
      "measured_at": "2026-09-10T11:08:49Z",
      "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": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 1346.9862893086279,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.395215158594592,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:qwen-qwen3-7-plus:c57dfba2bd8782fc",
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 22,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 43,
      "max_score": null,
      "measured_at": "2026-08-04T23:49:57Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1360.7360649255008,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.224037847715838,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:deepseek-deepseek-v4-pro-0813:62f039a975dbbc18",
      "capped_draws": 34,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 34,
      "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": 50,
      "max_score": null,
      "measured_at": "2026-09-10T11:09:23Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1335.8049891606988,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.818376109573915,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:z-ai-glm-5-2:51bd53334ebd6ddf",
      "capped_draws": 69,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 120,
      "draws": 69,
      "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": 96,
      "max_score": null,
      "measured_at": "2026-09-10T09:56:11Z",
      "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": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1341.5824373344149,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.661124622687225,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 10.945418121959325,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 553,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:google-gemini-3-6-flash:497c5e32f5a0da50",
      "capped_draws": 147,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 199,
      "draws": 147,
      "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": 272,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:14Z",
      "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": 553,
      "rating_method": "sequential_elo",
      "raw_elo": 1282.3886606251967,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.416793040873507,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 134
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 182,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:cohere-north-mini-code:bf20f7708e3f608c",
      "capped_draws": 84,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 84,
      "draws": 84,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 80,
      "max_score": null,
      "measured_at": "2026-08-05T05:09:16Z",
      "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": 182,
      "rating_method": "sequential_elo",
      "raw_elo": 1297.9536523160737,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.207095835838984,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.908556341051073,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:qwen-qwen3-8-2-4t-a95b:2caf8bc899f551f3",
      "capped_draws": 67,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 67,
      "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": 39,
      "max_score": null,
      "measured_at": "2026-09-10T09:56:53Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1279.1252646960281,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.13261343260962,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 121,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:meta-muse-spark-1-3:b665bb24258fc911",
      "capped_draws": 45,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 45,
      "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": 56,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:12Z",
      "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": 121,
      "rating_method": "sequential_elo",
      "raw_elo": 1224.6314436184432,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.663314448241664,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.5178730212592662,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:thinkingmachines-inkling-small:2a1c609d5f09a424",
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "draws": 29,
      "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": 76,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:12Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1217.2337078268613,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.22269275083169,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 202,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-6-luna:1c8c41335b2357b1",
      "capped_draws": 50,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "draws": 50,
      "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": 125,
      "max_score": null,
      "measured_at": "2026-09-10T10:02:20Z",
      "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": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 1197.0126079825945,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 19.061355620043653,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 198,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:thinkingmachines-inkling:70a9ac993f011430",
      "capped_draws": 71,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 93,
      "draws": 71,
      "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": 107,
      "max_score": null,
      "measured_at": "2026-08-05T05:09:23Z",
      "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": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1208.8856537756806,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 19.0569181003493,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.251875136730032,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:qwen-qwen3-8-max:3a653d034173d2f2",
      "capped_draws": 40,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 40,
      "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": 78,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:21Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1180.193855108586,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.134579252744338,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:google-gemini-3-1-flash-lite:890697e687a48241",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T03:26:44Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1195.0228351994263,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.062052955412074,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:deepseek-deepseek-v4-flash:b05f493f9c8d196b",
      "capped_draws": 38,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 38,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:10Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1179.7962359680705,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 16.963778223663805,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:bytedance-seed-seed-2-0-code:95b26b11b0986534",
      "capped_draws": 40,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 40,
      "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": 74,
      "max_score": null,
      "measured_at": "2026-09-10T10:05:22Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1163.7794884300404,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 15.646558344470218,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:o3:647217df3b12bb67",
      "capped_draws": 81,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 96,
      "draws": 81,
      "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": 172,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:32Z",
      "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": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1127.6524674454595,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 13.652811210043236,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 104,
      "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": 52,
      "draws": 38,
      "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": "2026-09-10T10:05:37Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1776.8781358681929,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 69.24351690590547,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 46,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-09-10T10:00:00Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1672.6595864434637,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.47588011557324,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 47
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 120,
      "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": 60,
      "draws": 45,
      "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": 7,
      "max_score": null,
      "measured_at": "2026-08-05T04:33:25Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1665.9022944138023,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.062164269002736,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 20.294267162641567,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:qwen-qwen3-7-max:7378b9f3cb87014a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 45,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 5,
      "max_score": null,
      "measured_at": "2026-08-04T20:03:05Z",
      "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": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.3189852487574,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.63292970387716,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:claude-opus-4-5:11b2bcd9aa32f256",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 58,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 8,
      "max_score": null,
      "measured_at": "2026-08-04T21:44:58Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.6675869461267,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 16.904129430402378,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:8ba9ac7e5b78b94d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "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": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 5,
      "max_score": null,
      "measured_at": "2026-08-03T08:48:42Z",
      "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": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.8783062336413,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 16.473094673491183,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:claude-opus-4-8:6a24675422272c49",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 54,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 1,
      "max_score": null,
      "measured_at": "2026-08-05T02:59:59Z",
      "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": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.1858427728368,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 15.08783877564788,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:google-gemini-3-1-flash-lite:890697e687a48241",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "draws": 48,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T03:32:23Z",
      "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": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.7142636458952,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 14.474268235287061,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 26.264004201400486,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:qwen-qwen3-7-plus:c57dfba2bd8782fc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 74,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 0,
      "max_score": null,
      "measured_at": "2026-08-05T02:59:50Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.2664311879878,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 14.181701766649182,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-5-5:8d8c6268a221d9ee",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 58,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T23:05:09Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.3280306730896,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 13.936024036303673,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 202,
      "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": 77,
      "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": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-09-10T09:57:20Z",
      "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": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.101689505752,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 13.272080636024716,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-5-4-mini:8b748b4207b1c84c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 59,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T22:55:23Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.5016442990093,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.418449045966476,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "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": 36,
      "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": "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": 7,
      "max_score": null,
      "measured_at": "2026-08-05T04:33:30Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.0193405271866,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.336409573070739,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:nex-agi-nex-n2-pro:66b75a517d8692bb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 55,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 7,
      "max_score": null,
      "measured_at": "2026-08-05T04:32:40Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.9810619922746,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.252825466946847,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:minimax-minimax-m3:ce3665e0f9c1f1b1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 26,
      "draws": 52,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 2,
      "max_score": null,
      "measured_at": "2026-08-05T04:33:21Z",
      "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": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.9568968469735,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.190471042456242,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-5-4-nano:2d8b3620ce9c297f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 66,
      "draws": 121,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:33:25Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.8925253457724,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.179369637744257,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 17.416580872281934,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "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": 66,
      "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": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-09-10T06:14:22Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.1881617549652,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 11.73718454940338,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-4-1:fccd725c87f1cbd8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 52,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 11,
      "max_score": null,
      "measured_at": "2026-08-05T04:33:30Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.8127849964237,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 11.682283349084813,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 130,
      "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": 65,
      "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": "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": "2026-09-10T10:09:03Z",
      "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": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.5392311464016,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 11.392747323534184,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 268,
      "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": 99,
      "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": "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": 40,
      "max_score": null,
      "measured_at": "2026-09-10T09:53:50Z",
      "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": 268,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.8383584594383,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 11.367330732070096,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 166,
      "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": 63,
      "draws": 149,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-09-10T09:44:57Z",
      "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": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.6038125675204,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 11.223439055353664,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 136,
      "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": 64,
      "draws": 120,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:37Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.6475719484033,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 11.191453740660169,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 46,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:xiaomi-mimo-v2-5:a7d613e15ebacf2f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 45,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 1,
      "max_score": null,
      "measured_at": "2026-07-31T02:24:42Z",
      "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": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.4229747689012,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.940010823479835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 352,
      "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": 176,
      "draws": 297,
      "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": 43,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:40Z",
      "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": 352,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.5194835765851,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.84501570624497,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.909379571113583,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "draws": 104,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-09-10T06:14:09Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.1968307019079,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.355871463342384,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "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": 53,
      "draws": 99,
      "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": 7,
      "max_score": null,
      "measured_at": "2026-09-10T04:39:29Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.9891675947683,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.263403044539475,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 174,
      "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": 66,
      "draws": 163,
      "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": 10,
      "max_score": null,
      "measured_at": "2026-09-10T07:14:16Z",
      "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": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.1410268131199,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.188518904480844,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 3,
      "attempted_matches": 204,
      "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": 102,
      "draws": 198,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:59Z",
      "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": 204,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.301070546453,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.165756558589774,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 15.654503924413575,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 249,
      "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": 87,
      "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": "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": 37,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:45Z",
      "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": 249,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.2968136986608,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.025497046336621,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 106,
      "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": 53,
      "draws": 101,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-09-10T09:50:56Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.2790794804664,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 9.955451026536553,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 102,
      "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": 2,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:58Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.5690635873218,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 9.761584645888398,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 454,
      "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": 156,
      "draws": 419,
      "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": 32,
      "max_score": null,
      "measured_at": "2026-09-10T09:49:08Z",
      "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": 1433.2751055672807,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 9.623986038775216,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 88,
      "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": 43,
      "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": "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": 3,
      "max_score": null,
      "measured_at": "2026-08-05T04:33:16Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.2026041849722,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 9.449979970240136,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "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": 55,
      "draws": 102,
      "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": 4,
      "max_score": null,
      "measured_at": "2026-09-10T07:14:22Z",
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.0385599177885,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 9.318441010342715,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "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": 41,
      "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": "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": 5,
      "max_score": null,
      "measured_at": "2026-08-05T04:26:48Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.1572953479408,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 8.990579277651428,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 112,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-09-10T07:13:19Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.1967788196498,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 8.860426297576485,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 462,
      "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": 161,
      "draws": 418,
      "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": 40,
      "max_score": null,
      "measured_at": "2026-09-10T09:49:09Z",
      "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": 462,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.613616977331,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 8.821204616548417,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 144,
      "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": 72,
      "draws": 130,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:59Z",
      "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": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.8897885177287,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 8.345895178371906,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 168,
      "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": 64,
      "draws": 147,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:56Z",
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.894017870154,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 8.247425935777672,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 104,
      "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": 52,
      "draws": 93,
      "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": 4,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:46Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.2773847293352,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 8.088342646823264,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 96,
      "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": 6,
      "max_score": null,
      "measured_at": "2026-09-10T07:13:17Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.2629477789696,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 8.085742846285687,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:tencent-hy3-preview:e682bc091589ac52",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 26,
      "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": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T02:27:36Z",
      "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": 52,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.3962138369807,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 7.405950095136704,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 24.930281974344517,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "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": 55,
      "draws": 102,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-09-10T06:12:24Z",
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.3963585232377,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 7.401997425923536,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:inclusionai-ling-3-0-flash:fde230dc0f90d703",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 90,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 7,
      "max_score": null,
      "measured_at": "2026-08-05T04:27:03Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.4826319119566,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 7.0150208382150785,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 94,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:33Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.0357341877234,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 6.964348588339904,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 104,
      "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": 52,
      "draws": 90,
      "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": 6,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:43Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.2710673446647,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 6.646568053595592,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 117,
      "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": 56,
      "draws": 103,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:44Z",
      "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": 117,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.8623852821136,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 6.07109411954341,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.2787308949161655,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 168,
      "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": 64,
      "draws": 130,
      "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": 33,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:43Z",
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.789468639564,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 3.906687867060584,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 138,
      "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": 66,
      "draws": 34,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:19Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1867.1321084211895,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 76.3726878991664,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "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": 66,
      "draws": 57,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-09-10T10:58:46Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1677.1243031299484,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 56.603672479674294,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 130,
      "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": 65,
      "draws": 25,
      "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": 39,
      "max_score": null,
      "measured_at": "2026-08-05T05:24:31Z",
      "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": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1580.2505939427776,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.00659226242805,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 17.8435026888779,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:tencent-hy4-preview:9b637fbe1929d4b6",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 55,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-09-10T10:51:41Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1551.2923629511429,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.511717852618325,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-4-1:fccd725c87f1cbd8",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 18,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 19,
      "max_score": null,
      "measured_at": "2026-08-05T04:02:51Z",
      "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": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.346999402338,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.06053158843793,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 152,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:z-ai-glm-5-3-flash:1c774d2a8faa3025",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 76,
      "draws": 49,
      "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": 63,
      "max_score": null,
      "measured_at": "2026-09-10T03:39:37Z",
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.4143934644067,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.207884772462265,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 270,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:moonshotai-kimi-k3:5a54aec150052f73",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "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": "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": 105,
      "max_score": null,
      "measured_at": "2026-09-10T07:38:27Z",
      "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": 270,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.2359495190115,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.089418073261065,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 1,
      "attempted_matches": 154,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:qwen-qwen3-8-flash:2ed602cefebb326c",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 53,
      "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": 65,
      "max_score": null,
      "measured_at": "2026-09-10T10:49:31Z",
      "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": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.3440787059294,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 40.141482789051,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 564,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:google-gemini-3-6-flash:497c5e32f5a0da50",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 210,
      "draws": 169,
      "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": 192,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:09Z",
      "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": 563,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.0737878225204,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.31324742201342,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:claude-opus-4-5:11b2bcd9aa32f256",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 43,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 13,
      "max_score": null,
      "measured_at": "2026-08-05T02:50:27Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.9730430010436,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 38.77747256709314,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 210,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:claude-sonnet-5:5d48f6168d64e7fe",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 86,
      "draws": 73,
      "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": 79,
      "max_score": null,
      "measured_at": "2026-09-10T10:49:31Z",
      "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": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.3697647442227,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 38.22889075944164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 254,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:meta-muse-spark-1-2:772fc6bb6f83c6c9",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 97,
      "draws": 41,
      "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": 110,
      "max_score": null,
      "measured_at": "2026-09-10T08:23:31Z",
      "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": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.219015697014,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.43165107800999,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-4-nano:2d8b3620ce9c297f",
      "capped_draws": 0,
      "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": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:02:45Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.2178560792047,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.07546402146493,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 284,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:google-gemini-3-5-flash-lite:d8ea2a1333ff0452",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 99,
      "draws": 78,
      "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": 96,
      "max_score": null,
      "measured_at": "2026-09-10T11:01:22Z",
      "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": 284,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.427549109553,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 36.970068726699864,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:minimax-minimax-m3:ce3665e0f9c1f1b1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 26,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 20,
      "max_score": null,
      "measured_at": "2026-08-05T03:55:23Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.939205942563,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 36.838386025548644,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:google-gemini-3-8-flash:bf006bcd6ccb81c6",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "draws": 40,
      "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": 64,
      "max_score": null,
      "measured_at": "2026-09-10T08:26:53Z",
      "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": 149,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.9781721136667,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 36.71877479296601,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:thinkingmachines-inkling:70a9ac993f011430",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 60,
      "draws": 55,
      "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": 31,
      "max_score": null,
      "measured_at": "2026-08-05T05:16:45Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.7385328418418,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 36.30519910226115,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-6-sol:34bccf96d771d2e5",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 91,
      "draws": 87,
      "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": 84,
      "max_score": null,
      "measured_at": "2026-09-10T09:46:08Z",
      "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": 241,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.111465965465,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.47859920538773,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:qwen-qwen3-8-2-4t-a95b:2caf8bc899f551f3",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "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": "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": 61,
      "max_score": null,
      "measured_at": "2026-09-10T08:25:04Z",
      "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": 131,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.4206644122155,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.18796927707111,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 142,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:bytedance-seed-seed-2-0-code:95b26b11b0986534",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 68,
      "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": "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": 64,
      "max_score": null,
      "measured_at": "2026-09-10T06:07:18Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.26607299235,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.82242746606155,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 164,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:meta-muse-spark-1-3:b665bb24258fc911",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "draws": 38,
      "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": 55,
      "max_score": null,
      "measured_at": "2026-09-10T06:52:41Z",
      "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": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.393382702446,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.5705964315616,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-4-mini:8b748b4207b1c84c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 55,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:03:00Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.7645713367565,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.349868844232375,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:xiaomi-mimo-v2-5:a7d613e15ebacf2f",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "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": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 19,
      "max_score": null,
      "measured_at": "2026-08-05T04:02:34Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.5650571562767,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.912938053620756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:nex-agi-nex-n2-pro:66b75a517d8692bb",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 19,
      "draws": 26,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 8,
      "max_score": null,
      "measured_at": "2026-08-03T15:07:00Z",
      "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": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.8177473760302,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.75354537169144,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 32.49928516630233,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 144,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:inception-mercury-2-5-preview:ae4030f1f9433705",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 72,
      "draws": 50,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-09-10T08:26:27Z",
      "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": 143,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.9077002269778,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.687732040284814,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 52,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:8ba9ac7e5b78b94d",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 24,
      "draws": 28,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 12,
      "max_score": null,
      "measured_at": "2026-08-05T03:54:51Z",
      "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": 52,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.1418660952263,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.12832035449617,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 24.930281974344517,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:tencent-hy3-preview:e682bc091589ac52",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 22,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:49:50Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.4673153903937,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.307974629209557,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 46,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:qwen-qwen3-7-max:7378b9f3cb87014a",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 21,
      "draws": 37,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 5,
      "max_score": null,
      "measured_at": "2026-08-03T04:31:38Z",
      "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": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.388701186896,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.86368222336517,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 208,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:z-ai-glm-5-2:51bd53334ebd6ddf",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 104,
      "draws": 96,
      "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": 65,
      "max_score": null,
      "measured_at": "2026-09-10T10:53:32Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.8661589852445,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.699708107136836,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 18.196593649245422,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1182,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:stealth-ox-alpha:2a6c37bfc1ea9a10",
      "capped_draws": 70,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 8,
      "distinct_rated_opponents": 589,
      "draws": 619,
      "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": 300,
      "max_score": null,
      "measured_at": "2026-09-10T11:01:03Z",
      "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": 1176,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.9381118969159,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.80876763063011,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 257
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 140,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:deepseek-deepseek-v4-pro:ff3e59d607a4ac18",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 70,
      "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-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": 37,
      "max_score": null,
      "measured_at": "2026-09-10T05:13:50Z",
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.4734243744404,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.588595959202145,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 353,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:poolside-laguna-s-2-1:834cbfa8b37e299a",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 142,
      "draws": 149,
      "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": 109,
      "max_score": null,
      "measured_at": "2026-09-10T08:23:32Z",
      "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": 353,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.6522280882073,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.541446134255093,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.385286799032644,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-5:8d8c6268a221d9ee",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "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-5.5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:23:57Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.1227478123901,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.247491079096818,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:z-ai-glm-5-3:d95da7acd9780380",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 64,
      "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": 34,
      "max_score": null,
      "measured_at": "2026-09-10T10:46:15Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.0235523274969,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.22983490746917,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:deepseek-deepseek-v4-pro-0813:62f039a975dbbc18",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "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-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": 42,
      "max_score": null,
      "measured_at": "2026-09-10T10:53:34Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.4341881071348,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.960429231630975,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:meta-muse-glimmer-30b:5f799292ad06c854",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 65,
      "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": 35,
      "max_score": null,
      "measured_at": "2026-09-10T10:54:45Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.0678585135524,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.71422878659438,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 144,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:thinkingmachines-inkling-small:2a1c609d5f09a424",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 70,
      "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": "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": 21,
      "max_score": null,
      "measured_at": "2026-09-10T10:44:28Z",
      "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": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.6149135142155,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.77922001165981,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:openai-gpt-oss-120b:e4864d083f4798c2",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 49,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-09-10T10:51:43Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1397.508419898018,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.51154808681522,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 1,
      "attempted_matches": 34,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:8548115fcae6ae84",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 17,
      "draws": 24,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T02:59:43Z",
      "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": 34,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.039014779849,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.845947820192375,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 40.76542547285167,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "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": 66,
      "draws": 120,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-09-10T10:48:58Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1390.7525411421307,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.808645008214626,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 130,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:meituan-longcat-2-0:8409ccd1edce8105",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 61,
      "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": "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": 40,
      "max_score": null,
      "measured_at": "2026-08-05T05:24:42Z",
      "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": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1394.540988611574,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.677678742623275,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 17.928761438070325,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:claude-fable-5:7f6b2a08dddc3940",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 76,
      "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": 35,
      "max_score": null,
      "measured_at": "2026-09-10T10:53:25Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1377.4522396482325,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.424839406577654,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-6-terra:9663b021bc677328",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 79,
      "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": 37,
      "max_score": null,
      "measured_at": "2026-09-10T10:54:56Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1373.9942208454174,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.065056149626912,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "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": 66,
      "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": "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": 42,
      "max_score": null,
      "measured_at": "2026-09-10T10:54:11Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1365.9686904077316,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.230054478358582,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 214,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-4:86f20e721b83e093",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 115,
      "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": 68,
      "max_score": null,
      "measured_at": "2026-09-10T10:54:31Z",
      "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": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1356.2119695135434,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.985334973637,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 143,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:qwen-qwen3-8-max:3a653d034173d2f2",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 68,
      "draws": 76,
      "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": 37,
      "max_score": null,
      "measured_at": "2026-09-10T10:49:44Z",
      "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": 143,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.2533801623117,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.67194141579853,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 156,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:inclusionai-ling-3-0-flash:fde230dc0f90d703",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 60,
      "draws": 64,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 63,
      "max_score": null,
      "measured_at": "2026-08-05T05:24:14Z",
      "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": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1363.2902103171728,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.87323324614359,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 12.558578456903872,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 210,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-6-luna:1c8c41335b2357b1",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "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-5.6-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": 74,
      "max_score": null,
      "measured_at": "2026-09-10T11:01:22Z",
      "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": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1301.546731566777,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 18.271013266534894,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:google-gemini-3-5-flash:8f1504913d7602c4",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 39,
      "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": 72,
      "max_score": null,
      "measured_at": "2026-09-10T11:00:53Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1219.7338249759325,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 9.01531471986587,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 268,
      "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": 96,
      "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": "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": 174,
      "max_score": null,
      "measured_at": "2026-09-10T11:01:12Z",
      "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": 268,
      "rating_method": "sequential_elo",
      "raw_elo": 1122.7881106713216,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 114,
      "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": 57,
      "draws": 16,
      "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": 21,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:02Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1818.160443932235,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 83.51151151272518,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "draws": 40,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-09-10T09:56:27Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1625.6665151364496,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 51.654769151687816,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "draws": 35,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-09-10T09:52:53Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1582.7585448506213,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.553723611281114,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "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": 34,
      "draws": 37,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-05T03:47:20Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1558.1767288584622,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 38.689256035103924,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 138,
      "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": 69,
      "draws": 52,
      "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": 38,
      "max_score": null,
      "measured_at": "2026-08-05T03:54:42Z",
      "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": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.3733833554654,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 36.957881306791684,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 16.016004726288628,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:claude-opus-4-5:11b2bcd9aa32f256",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 24,
      "draws": 27,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 11,
      "max_score": null,
      "measured_at": "2026-07-31T02:32:56Z",
      "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": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.4826607753314,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.43189092678594,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 27.678571428571434,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 266,
      "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": 98,
      "draws": 129,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-09-10T07:13:18Z",
      "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": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.7041047211976,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.944449816020683,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 464,
      "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": 170,
      "draws": 286,
      "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": 87,
      "max_score": null,
      "measured_at": "2026-09-10T09:50:35Z",
      "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": 458,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.1763575802674,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.70885960900305,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:xiaomi-mimo-v2-5:a7d613e15ebacf2f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 52,
      "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",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 5,
      "max_score": null,
      "measured_at": "2026-07-31T02:31:22Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.8323226969433,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.37278856274247,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 25.077594640911812,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "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": 66,
      "draws": 61,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-09-10T07:13:46Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.39421628638,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.362787798826755,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 46,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:tencent-hy3-preview:e682bc091589ac52",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 30,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:48:07Z",
      "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": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1517.7254552578606,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.308115130799013,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 142,
      "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": 71,
      "draws": 83,
      "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": 42,
      "max_score": null,
      "measured_at": "2026-09-10T05:30:24Z",
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.3460835073072,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.566192792814146,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:gpt-5-5:8d8c6268a221d9ee",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 49,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:02:26Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.6470368880275,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.32831260800084,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 222,
      "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": 90,
      "draws": 139,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-09-10T07:35:18Z",
      "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": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.1129279334805,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.982497616728754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:nex-agi-nex-n2-pro:66b75a517d8692bb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 67,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 6,
      "max_score": null,
      "measured_at": "2026-08-05T02:13:44Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.8528084385841,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.572458734081646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "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": 66,
      "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": "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": 39,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:57Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.158184486332,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.34481954197784,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 143,
      "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": 69,
      "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": "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": 15,
      "max_score": null,
      "measured_at": "2026-09-10T10:08:59Z",
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.191931895889,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.223754441408413,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 3,
      "attempted_matches": 366,
      "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": 183,
      "draws": 251,
      "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": 61,
      "max_score": null,
      "measured_at": "2026-09-10T09:51:11Z",
      "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": 365,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.7215980170065,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.868002662206536,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.4112147100384131,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 61,
      "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": "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": 46,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:18Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.5658380642715,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.52152714323692,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:google-gemma-4-31b-it:a05cbdb73d0f0757",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 55,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 8,
      "max_score": null,
      "measured_at": "2026-08-05T03:48:11Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.423921097945,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.431101136188207,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:claude-opus-4-8:6a24675422272c49",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "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-4-8",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 11,
      "max_score": null,
      "measured_at": "2026-08-05T03:47:33Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.4910188022745,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.2110900930888,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:gpt-5-4-mini:8b748b4207b1c84c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 46,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:24:08Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.1917518609623,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.617653837866694,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:inclusionai-ling-3-0-flash:fde230dc0f90d703",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 86,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 5,
      "max_score": null,
      "measured_at": "2026-08-05T05:33:25Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.8882535679693,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.22863025415459,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:8548115fcae6ae84",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 22,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-30T18:04:01Z",
      "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": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.14911205402,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.201140195303772,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 30.785599249992988,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "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": 84,
      "draws": 145,
      "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": 51,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:38Z",
      "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": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.7324707966186,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.12586844413473,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 497,
      "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": 180,
      "draws": 357,
      "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": 101,
      "max_score": null,
      "measured_at": "2026-09-10T09:52:12Z",
      "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": 497,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.9768231349922,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.22733450545151,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 1,
      "attempted_matches": 200,
      "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": 100,
      "draws": 128,
      "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": 55,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:54Z",
      "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": 199,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.4936244989651,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.825666754280896,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "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": 66,
      "draws": 79,
      "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": 36,
      "max_score": null,
      "measured_at": "2026-09-10T09:57:26Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.0204773592366,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.019165184642294,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 56,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:qwen-qwen3-7-plus:c57dfba2bd8782fc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 45,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 8,
      "max_score": null,
      "measured_at": "2026-08-04T23:28:00Z",
      "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": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.4292622210753,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.87218750063355,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "draws": 96,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-09-10T07:20:36Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.9682278137316,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.743112742729135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "draws": 85,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:18Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.5158485739823,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.337256754953387,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 196,
      "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": 74,
      "draws": 137,
      "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": 32,
      "max_score": null,
      "measured_at": "2026-09-10T09:54:08Z",
      "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": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.7907735203491,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 21.52240960642956,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 126,
      "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": 63,
      "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": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-09-10T09:52:42Z",
      "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": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.9495004871246,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 21.38393789540447,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 142,
      "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": 69,
      "draws": 95,
      "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": 26,
      "max_score": null,
      "measured_at": "2026-08-05T03:47:58Z",
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.689412717466,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 21.233388940349045,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 15.179828253878973,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 94,
      "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": 14,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:50Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.6029710194987,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.139382489297006,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "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": 57,
      "draws": 76,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:34Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.5683313615027,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 19.863520529847257,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 245,
      "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": 91,
      "draws": 138,
      "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": 79,
      "max_score": null,
      "measured_at": "2026-09-10T07:15:32Z",
      "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": 245,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.4089666754899,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 19.803571551585858,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 114,
      "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": 57,
      "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": "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": 20,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:32Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.006254461214,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 19.108520570352844,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 188,
      "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": 69,
      "draws": 132,
      "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": 30,
      "max_score": null,
      "measured_at": "2026-09-10T09:49:10Z",
      "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": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.720030490479,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 19.09499131510905,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 234,
      "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": 82,
      "draws": 187,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:59Z",
      "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": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.0682594652842,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 18.656566613036805,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 114,
      "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": 57,
      "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": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-09-10T09:48:58Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.9814194878577,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.78045219003907,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 128,
      "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": 64,
      "draws": 106,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-09-10T07:14:15Z",
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.3850925129989,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.529864794901115,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 216,
      "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": 108,
      "draws": 139,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-09-10T09:52:42Z",
      "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": 216,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.2379740354415,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 16.949774220889857,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 14.470133891109075,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 130,
      "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": 59,
      "draws": 103,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:22Z",
      "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": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.0555206532733,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 16.196026786301488,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:gpt-4-1:fccd725c87f1cbd8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 48,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 12,
      "max_score": null,
      "measured_at": "2026-08-05T00:50:32Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.8618510492545,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 15.428003461676202,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "draws": 70,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:59Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.7280216533547,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 13.104662042950768,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 20
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04: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": 57,
      "draws": 82,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-09-10T09:50:29Z",
      "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": 1378.4663573739215,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.74443090510793,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": "2026-09-10T10:39:45Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 2090.9059975494283,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 95.24447704187754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 114
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 10,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:43Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 2014.1772003359092,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 89.2299699098686,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 133,
      "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": 64,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:05Z",
      "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": 133,
      "rating_method": "sequential_elo",
      "raw_elo": 2006.4991720318374,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 88.76990902930297,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 117
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 156,
      "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": 78,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-08-05T04:56:12Z",
      "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": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1918.6883869209828,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 81.06683069976471,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 12.51792189268726,
      "unilateral_faults": 0,
      "wins": 143
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 61,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:42Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1670.208226339689,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 62.26742230817677,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:claude-opus-4-5:11b2bcd9aa32f256",
      "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": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 30,
      "max_score": null,
      "measured_at": "2026-08-03T10:29:27Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1615.986901751882,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 57.33994820345935,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:8548115fcae6ae84",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T02:29:42Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1621.0647466868909,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 57.3153424952665,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 214,
      "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": 90,
      "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": 112,
      "max_score": null,
      "measured_at": "2026-09-09T22:57:25Z",
      "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": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1582.1244495483195,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 56.074890123705295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 335,
      "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": 127,
      "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": 154,
      "max_score": null,
      "measured_at": "2026-09-10T10:38:53Z",
      "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": 335,
      "rating_method": "sequential_elo",
      "raw_elo": 1571.0784225753098,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.636862652973036,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 181
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 152,
      "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": 76,
      "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": 55,
      "max_score": null,
      "measured_at": "2026-08-05T00:20:24Z",
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1575.3504369194993,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.10090278289114,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.360606452268916,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 61,
      "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": 76,
      "max_score": null,
      "measured_at": "2026-09-10T04:38:49Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1563.9688531542206,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.96295151563907,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "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": 92,
      "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": 131,
      "max_score": null,
      "measured_at": "2026-09-10T03:56:59Z",
      "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": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.8020800815002,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.37102488938938,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 156,
      "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": 78,
      "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": 84,
      "max_score": null,
      "measured_at": "2026-09-10T07:13:19Z",
      "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": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.1713370273924,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 51.56007348257478,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:qwen-qwen3-7-plus:c57dfba2bd8782fc",
      "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": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 36,
      "max_score": null,
      "measured_at": "2026-08-05T01:37:44Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.1416526227213,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.37567398128637,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "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": 67,
      "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": 78,
      "max_score": null,
      "measured_at": "2026-09-10T08:08:17Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.4033276853204,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.36302806951727,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:nex-agi-nex-n2-pro:66b75a517d8692bb",
      "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": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 38,
      "max_score": null,
      "measured_at": "2026-08-03T11:29:18Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.644299345217,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.1453521622104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:qwen-qwen3-7-max:7378b9f3cb87014a",
      "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": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 44,
      "max_score": null,
      "measured_at": "2026-08-04T23:21:58Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.989498345392,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.97948143649212,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 38
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 194,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:xiaomi-mimo-v2-5:a7d613e15ebacf2f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 97,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 96,
      "max_score": null,
      "measured_at": "2026-08-03T14:20:34Z",
      "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": 194,
      "rating_method": "sequential_elo",
      "raw_elo": 1526.3456577110624,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.95050528925342,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 18.289400506511907,
      "unilateral_faults": 0,
      "wins": 98
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-5-5:8d8c6268a221d9ee",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:40:34Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.5004355757312,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.787345255628644,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 388,
      "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": 194,
      "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": 174,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:39Z",
      "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": 388,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.461141249657,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.214171810132676,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.0126757293056905,
      "unilateral_faults": 0,
      "wins": 214
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 176,
      "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": 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": "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": 88,
      "max_score": null,
      "measured_at": "2026-09-10T10:38:57Z",
      "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": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.3395710789268,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.348251895031375,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 635,
      "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": 219,
      "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": 291,
      "max_score": null,
      "measured_at": "2026-09-10T07:12:26Z",
      "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": 635,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.5951989347143,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.84746789517817,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 344
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:minimax-minimax-m3:ce3665e0f9c1f1b1",
      "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": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 46,
      "max_score": null,
      "measured_at": "2026-08-03T11:38:28Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.8637902645755,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.440218311437484,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 164,
      "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": 82,
      "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": 95,
      "max_score": null,
      "measured_at": "2026-09-10T08:06:46Z",
      "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": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.4581407186583,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.686593077752605,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 267,
      "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": 93,
      "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": 122,
      "max_score": null,
      "measured_at": "2026-09-10T04:38:52Z",
      "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": 267,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.2585433768318,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.41274737025844,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 230,
      "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": 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-5.6-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": 80,
      "max_score": null,
      "measured_at": "2026-09-10T05:27:35Z",
      "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": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.999852136446,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.24477513071418,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 150
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 43,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:01Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.3534727627618,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.64182972536665,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 57,
      "max_score": null,
      "measured_at": "2026-09-10T10:25:56Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.1675043060943,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.07854631545282,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:claude-opus-4-8:6a24675422272c49",
      "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": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 38,
      "max_score": null,
      "measured_at": "2026-08-03T14:20:21Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.9499590147173,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.46262973385445,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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:GB2-05:publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:8ba9ac7e5b78b94d",
      "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": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 37,
      "max_score": null,
      "measured_at": "2026-08-03T12:50:04Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.8923348583521,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.90940679325011,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 57,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:26Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1383.0705290094131,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.75968347765998,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-09-10T05:24:36Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1374.7864842662034,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.11032563550241,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "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": 85,
      "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": 158,
      "max_score": null,
      "measured_at": "2026-09-10T03:41:09Z",
      "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": 1349.1837565795022,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.997988417921604,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:tencent-hy3-preview:e682bc091589ac52",
      "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": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:56:04Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1362.0329257769195,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.51942114475686,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 34
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 238,
      "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": 119,
      "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": 151,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:06Z",
      "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": 1332.8693256406384,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.199708198410335,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.669186311838754,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 174,
      "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": 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": "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": 107,
      "max_score": null,
      "measured_at": "2026-08-05T01:30:14Z",
      "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": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1327.4143578677654,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.903535425620994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.573428145379982,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-5-4-mini:8b748b4207b1c84c",
      "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": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:40:16Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1295.479782930378,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.123645602053834,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 206,
      "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": 77,
      "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": 135,
      "max_score": null,
      "measured_at": "2026-09-10T10:38:51Z",
      "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": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1244.6897025475216,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.583608741898452,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 60,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:03Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1217.9429183062275,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.815896681391532,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-4-1:fccd725c87f1cbd8",
      "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": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 50,
      "max_score": null,
      "measured_at": "2026-08-05T03:40:43Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1222.6598405913285,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.4628692919667,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:google-gemma-4-31b-it:a05cbdb73d0f0757",
      "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": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 51,
      "max_score": null,
      "measured_at": "2026-08-05T02:32:27Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1201.6240382292942,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.766615824644276,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 206,
      "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": 76,
      "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": 137,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:04Z",
      "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": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1180.4517267849226,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.54821424333988,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 142,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-5-4-nano:2d8b3620ce9c297f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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-5.4-nano",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:56:12Z",
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1193.9987947074715,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.093974048156653,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 15.179828253878973,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:google-gemini-3-1-flash-lite:890697e687a48241",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T03:34:49Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1192.492164384378,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.721008341051526,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 120,
      "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": 60,
      "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": 89,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:03Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1162.6706570017993,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.483293774914944,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 158,
      "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": 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": "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": 111,
      "max_score": null,
      "measured_at": "2026-08-03T22:34:39Z",
      "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": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1142.237542324819,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.179848697832213,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 12.895291237259062,
      "unilateral_faults": 4,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 89,
      "max_score": null,
      "measured_at": "2026-09-10T10:38:57Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1131.9752508173779,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.07718621008026,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 94,
      "max_score": null,
      "measured_at": "2026-09-10T10:38:52Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1066.7098759830644,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 14.961257423631709,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05: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": 60,
      "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": 97,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:26Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1017.3234430605204,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 11.090024407811828,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 544,
      "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": 184,
      "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": 464,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:33Z",
      "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": 544,
      "rating_method": "sequential_elo",
      "raw_elo": 993.6783536394931,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.189281084335075,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 106,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:27Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 965.0191901221987,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 6.990073492948425,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "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": 62,
      "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": 128,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:15Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 873.907694545383,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 66,
      "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": 33,
      "draws": 3,
      "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": 3,
      "max_score": null,
      "measured_at": "2026-08-03T09:47:39Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1897.0527582969269,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 79.49418767823046,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 15,
      "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": 31,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:54Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1832.4555169206908,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 75.39655078902038,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 16,
      "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": 26,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:00Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1801.5308334075144,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 72.97814614584291,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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": "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": 51,
      "max_score": null,
      "measured_at": "2026-09-10T10:00:11Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1752.85806974237,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 69.17178746172216,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "draws": 10,
      "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": 45,
      "max_score": null,
      "measured_at": "2026-09-10T05:40:23Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1688.7833998028116,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 64.18475015909165,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "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": 90,
      "draws": 17,
      "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": 90,
      "max_score": null,
      "measured_at": "2026-09-10T01:40:11Z",
      "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": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1629.395387453824,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 60.326020445609515,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 142,
      "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": 71,
      "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": "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": 88,
      "max_score": null,
      "measured_at": "2026-09-10T02:27:04Z",
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1610.3425038521104,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 58.27831291867289,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:gpt-4-1:fccd725c87f1cbd8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 9,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 27,
      "max_score": null,
      "measured_at": "2026-08-03T13:58:04Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1591.8487355395282,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.88308492443146,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 318,
      "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": 103,
      "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": "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": 116,
      "max_score": null,
      "measured_at": "2026-09-10T07:35:06Z",
      "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": 318,
      "rating_method": "sequential_elo",
      "raw_elo": 1567.1387534647272,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.764102739590896,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 566,
      "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": 195,
      "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": "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": 272,
      "max_score": null,
      "measured_at": "2026-09-10T01:44:23Z",
      "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": 566,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.7066470450266,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.547243139429334,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 286
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "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": 68,
      "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": "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": 74,
      "max_score": null,
      "measured_at": "2026-09-10T06:18:24Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.0003438184813,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.268094704811084,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:claude-opus-4-8:6a24675422272c49",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 8,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 23,
      "max_score": null,
      "measured_at": "2026-08-05T01:59:52Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1558.851644552222,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.0458282808096,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 158,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06: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": 79,
      "draws": 4,
      "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": 88,
      "max_score": null,
      "measured_at": "2026-09-10T07:29:21Z",
      "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": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.5551640009767,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 52.643022639184814,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 156,
      "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": 78,
      "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": "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": 80,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:25Z",
      "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": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.1409844045036,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 52.04746013492715,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 251,
      "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": 90,
      "draws": 7,
      "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": 110,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:32Z",
      "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": 251,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.5430167446611,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 51.74464823357423,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 134
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 140,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:gpt-5-4-nano:2d8b3620ce9c297f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 68,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:41:10Z",
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.7984680553782,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 51.6471832448803,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 15.8742369405862,
      "unilateral_faults": 0,
      "wins": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 146,
      "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": 73,
      "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": "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": 87,
      "max_score": null,
      "measured_at": "2026-09-10T07:32:19Z",
      "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": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.241400953843,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.3128908338914,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 323,
      "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": 106,
      "draws": 30,
      "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": 142,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:13Z",
      "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": 323,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.4668228591477,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.68684753126993,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 202,
      "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": 101,
      "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": "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": 92,
      "max_score": null,
      "measured_at": "2026-09-10T06:16:55Z",
      "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": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.6613947942544,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.009788801136246,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 312,
      "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": 104,
      "draws": 24,
      "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": 132,
      "max_score": null,
      "measured_at": "2026-09-10T05:33:33Z",
      "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": 312,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.074893914877,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.765690377579354,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 156
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:claude-opus-4-5:11b2bcd9aa32f256",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 5,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 32,
      "max_score": null,
      "measured_at": "2026-08-05T03:20:38Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.9694663520272,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.6630449859877,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 148,
      "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": 74,
      "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": "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": 53,
      "max_score": null,
      "measured_at": "2026-09-10T04:47:52Z",
      "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": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.1515439087545,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.3515218979427,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 3,
      "attempted_matches": 224,
      "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": 112,
      "draws": 24,
      "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": 96,
      "max_score": null,
      "measured_at": "2026-09-10T09:57:11Z",
      "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": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.452004165843,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.97848016268618,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.549881946921332,
      "unilateral_faults": 0,
      "wins": 104
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 184,
      "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": 90,
      "draws": 16,
      "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": 90,
      "max_score": null,
      "measured_at": "2026-08-05T04:32:58Z",
      "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": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.3276839958567,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.89316223345493,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.242236982581751,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 192,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:xiaomi-mimo-v2-5:a7d613e15ebacf2f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 94,
      "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": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 91,
      "max_score": null,
      "measured_at": "2026-08-05T03:20:33Z",
      "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": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.431952780135,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.87933046445113,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 17.343660385208338,
      "unilateral_faults": 0,
      "wins": 98
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "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": 83,
      "draws": 14,
      "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": 96,
      "max_score": null,
      "measured_at": "2026-09-10T09:57:11Z",
      "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": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.0180595611305,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.742957151306456,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 134,
      "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": 67,
      "draws": 7,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-09-10T02:26:59Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.156962894926,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.876252741029056,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 136,
      "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": 68,
      "draws": 9,
      "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": 56,
      "max_score": null,
      "measured_at": "2026-09-10T01:43:49Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.0307512062466,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.41688806132841,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:8ba9ac7e5b78b94d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "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": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 37,
      "max_score": null,
      "measured_at": "2026-08-03T09:47:39Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.373702874258,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.26617619713358,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 42
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 450,
      "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": 211,
      "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": "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": 267,
      "max_score": null,
      "measured_at": "2026-09-10T10:15:27Z",
      "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": 450,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.3196759557468,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.75760836120296,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 128,
      "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": 64,
      "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": 58,
      "max_score": null,
      "measured_at": "2026-09-10T04:04:06Z",
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1397.6542566136736,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.50715196387154,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:gpt-5-4-mini:8b748b4207b1c84c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "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-5.4-mini",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:29:03Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1387.7364854445989,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.92088394835182,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:google-gemini-3-1-flash-lite:890697e687a48241",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T01:58:27Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1382.3956787117227,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.06289260104517,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:google-gemma-4-31b-it:a05cbdb73d0f0757",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "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": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 41,
      "max_score": null,
      "measured_at": "2026-08-05T00:42:50Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1351.780972077647,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.109053054838675,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 46,
      "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": "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": 51,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:50Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1318.239164434667,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.87468051476392,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:qwen-qwen3-7-max:7378b9f3cb87014a",
      "capped_draws": 0,
      "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": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 45,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:50Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1317.7760054622622,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.4025425756531,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:8548115fcae6ae84",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T00:54:22Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1283.4075921095573,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.321722084104252,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:qwen-qwen3-7-plus:c57dfba2bd8782fc",
      "capped_draws": 0,
      "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": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 52,
      "max_score": null,
      "measured_at": "2026-08-05T03:19:33Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1248.3796837667817,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.97553839834991,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 550,
      "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": 178,
      "draws": 61,
      "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": 356,
      "max_score": null,
      "measured_at": "2026-09-10T10:09:09Z",
      "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": 550,
      "rating_method": "sequential_elo",
      "raw_elo": 1217.4900636368764,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.288928420260433,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 133
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "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": 42,
      "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": "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": 47,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:28Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1229.8219327403026,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.820507101588568,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "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": 75,
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-09-10T09:59:37Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1202.5637405728094,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.84086876363679,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:nex-agi-nex-n2-pro:66b75a517d8692bb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "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": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 48,
      "max_score": null,
      "measured_at": "2026-08-05T03:20:18Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1212.3309448675193,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.946851868730132,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 272,
      "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": 89,
      "draws": 40,
      "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": 193,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:47Z",
      "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": 272,
      "rating_method": "sequential_elo",
      "raw_elo": 1129.6690678120026,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 21.41082453515432,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 1,
      "attempted_matches": 139,
      "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": 62,
      "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": "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": 100,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:23Z",
      "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": 139,
      "rating_method": "sequential_elo",
      "raw_elo": 1135.9434964465404,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 21.15098392596629,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 118,
      "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": 59,
      "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": 81,
      "max_score": null,
      "measured_at": "2026-09-10T10:05:07Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1135.9605316579625,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.92851700650774,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "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": 76,
      "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-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": 148,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:09Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1125.533713227516,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.816885503902856,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 118,
      "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": 59,
      "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": 74,
      "max_score": null,
      "measured_at": "2026-09-10T10:05:55Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1108.0482505341167,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 18.745691425032618,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 204,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:inclusionai-ling-3-0-flash:fde230dc0f90d703",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 78,
      "draws": 4,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 152,
      "max_score": null,
      "measured_at": "2026-08-03T14:04:05Z",
      "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": 204,
      "rating_method": "sequential_elo",
      "raw_elo": 1103.9436983097544,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 18.209581535374213,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.523431578963063,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 3,
      "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": 89,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:09Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1097.337741745947,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.908096945753098,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "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": 60,
      "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": "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": 93,
      "max_score": null,
      "measured_at": "2026-09-10T10:05:24Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1071.4948750931987,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 16.062391875633203,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "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": 62,
      "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": 7,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:32Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 2071.65343311513,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 97.61905921533831,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 117
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 25,
      "max_score": null,
      "measured_at": "2026-09-10T10:38:58Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1888.7253917920593,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 82.38006707268947,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 99
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "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": 33,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-03T14:13:52Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1788.427811410473,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 72.9341507961126,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 530,
      "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": 197,
      "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": 216,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:24Z",
      "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": 530,
      "rating_method": "sequential_elo",
      "raw_elo": 1679.6379373271573,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 65.89914757897805,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "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": 62,
      "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": 61,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:41Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1684.0539106103315,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 65.32971726850512,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 137,
      "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": 67,
      "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": 63,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:45Z",
      "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": 137,
      "rating_method": "sequential_elo",
      "raw_elo": 1680.3198610156614,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 65.16250365749241,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 60,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:41Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1636.2057518933793,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 61.34368150573174,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:nex-agi-nex-n2-pro:66b75a517d8692bb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 20,
      "max_score": null,
      "measured_at": "2026-08-03T10:15:02Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1643.2683262324292,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 60.77934776395481,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 270,
      "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": 101,
      "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": 104,
      "max_score": null,
      "measured_at": "2026-09-10T03:12:25Z",
      "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": 270,
      "rating_method": "sequential_elo",
      "raw_elo": 1607.2119914999753,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 59.88458279946914,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:qwen-qwen3-7-max:7378b9f3cb87014a",
      "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": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 22,
      "max_score": null,
      "measured_at": "2026-08-03T08:56:19Z",
      "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": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1630.9732967737627,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 59.55002702144701,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 186,
      "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": 93,
      "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": 100,
      "max_score": null,
      "measured_at": "2026-09-10T07:08:48Z",
      "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": 186,
      "rating_method": "sequential_elo",
      "raw_elo": 1548.4272881975826,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.57488465434671,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:claude-opus-4-8:6a24675422272c49",
      "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": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 29,
      "max_score": null,
      "measured_at": "2026-08-05T01:45:01Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.40103047392,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.07809949631,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 178,
      "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": 89,
      "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": 87,
      "max_score": null,
      "measured_at": "2026-09-10T08:06:59Z",
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1541.8464737999418,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.97280588441953,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:8ba9ac7e5b78b94d",
      "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": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 30,
      "max_score": null,
      "measured_at": "2026-08-05T02:50:32Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.9374591439505,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.03980999081365,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 268,
      "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": 134,
      "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": 141,
      "max_score": null,
      "measured_at": "2026-09-10T07:11:41Z",
      "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": 268,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.5972933214946,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.75736719314747,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 12.837139418723911,
      "unilateral_faults": 0,
      "wins": 127
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-4-1:fccd725c87f1cbd8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 33,
      "max_score": null,
      "measured_at": "2026-08-03T14:04:15Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1517.0750056649872,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.266694773888176,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 31
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 160,
      "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": 75,
      "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": 87,
      "max_score": null,
      "measured_at": "2026-08-04T01:46:38Z",
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.128045469491,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.106011352032695,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.244710982631887,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 557,
      "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": 188,
      "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": 264,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:12Z",
      "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": 553,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.5671295846262,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.274306768900956,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 289
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 176,
      "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": 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": "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": 89,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:43Z",
      "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": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.4006055300267,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.08988614590849,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 261,
      "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": 95,
      "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": 113,
      "max_score": null,
      "measured_at": "2026-09-10T07:11:19Z",
      "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": 261,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.5273767081653,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.046939930059665,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 150,
      "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": 75,
      "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": 82,
      "max_score": null,
      "measured_at": "2026-09-10T10:25:47Z",
      "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": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.3166092846598,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.20969665141295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:claude-opus-4-5:11b2bcd9aa32f256",
      "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": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 41,
      "max_score": null,
      "measured_at": "2026-08-05T01:37:35Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.726826181827,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.17467565559709,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-5-5:8d8c6268a221d9ee",
      "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": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:02:22Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.7629546063713,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.093227838491046,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 288,
      "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": 96,
      "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": 135,
      "max_score": null,
      "measured_at": "2026-09-10T05:23:43Z",
      "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": 288,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.1416955480029,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.781096360775045,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 216,
      "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": 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-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": 110,
      "max_score": null,
      "measured_at": "2026-09-10T04:00:04Z",
      "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": 216,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.974888101097,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.04906884876752,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 106
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "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": 64,
      "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": 55,
      "max_score": null,
      "measured_at": "2026-09-10T06:10:25Z",
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.4944080709313,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.920382254410434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 166,
      "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": 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": "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": 81,
      "max_score": null,
      "measured_at": "2026-08-05T05:16:33Z",
      "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": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.0098278142677,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.26122886658135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 10.807372224754609,
      "unilateral_faults": 0,
      "wins": 85
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 53,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:15Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1388.8368134317343,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 40.73637995542009,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:minimax-minimax-m3:ce3665e0f9c1f1b1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 41,
      "max_score": null,
      "measured_at": "2026-08-05T04:09:17Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1400.0415201193246,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 40.695604031124134,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 372,
      "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": 186,
      "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": 223,
      "max_score": null,
      "measured_at": "2026-09-10T10:38:57Z",
      "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": 372,
      "rating_method": "sequential_elo",
      "raw_elo": 1377.4600285305544,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.78862621321775,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 149
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "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": 82,
      "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": 132,
      "max_score": null,
      "measured_at": "2026-09-10T07:08:47Z",
      "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": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1366.7542420762652,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.6557227947306,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 206,
      "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": 77,
      "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": 111,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:44Z",
      "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": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1350.9626991135992,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 38.245619988996886,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 1,
      "attempted_matches": 140,
      "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": 70,
      "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": 75,
      "max_score": null,
      "measured_at": "2026-09-10T08:07:02Z",
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1350.283417023103,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.698846705657566,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 140,
      "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": 70,
      "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": 57,
      "max_score": null,
      "measured_at": "2026-09-10T01:25:22Z",
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1346.062927829242,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.34725489284307,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 138,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:xiaomi-mimo-v2-5:a7d613e15ebacf2f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 68,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 78,
      "max_score": null,
      "measured_at": "2026-08-03T22:56:47Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1348.8770201939483,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 36.376393155828296,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 2,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 280,
      "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": 96,
      "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": 163,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:32Z",
      "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": 280,
      "rating_method": "sequential_elo",
      "raw_elo": 1319.3894482362023,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.94359963093725,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 117
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-5-4-nano:2d8b3620ce9c297f",
      "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": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T11:10:49Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1330.5150146991402,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.20066576920315,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "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": 41,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-08-05T02:50:21Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1320.2237612604144,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.386630045412275,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 282,
      "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": 96,
      "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": 180,
      "max_score": null,
      "measured_at": "2026-09-10T10:25:51Z",
      "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": 282,
      "rating_method": "sequential_elo",
      "raw_elo": 1300.0532231004343,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.33981389682823,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07: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": 62,
      "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": 61,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:46Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1311.9620137214838,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.33225262601179,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:14Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1299.509218523322,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.294860836288024,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:cohere-north-mini-code:bf20f7708e3f608c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 69,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 98,
      "max_score": null,
      "measured_at": "2026-08-05T02:50:09Z",
      "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": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1307.793294134663,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.07868627119113,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 14.570138866854082,
      "unilateral_faults": 4,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 70,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:39Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1296.2785108029113,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.02572369793326,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:37Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1294.2455644828358,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.856367197016354,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "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": 65,
      "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": 76,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:24Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1281.5719820233626,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.934103720162618,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 72,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:29Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1269.2768040275703,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.7763211765297,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:google-gemma-4-31b-it:a05cbdb73d0f0757",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 49,
      "max_score": null,
      "measured_at": "2026-08-03T21:49:16Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1227.6442414952623,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.276982761125968,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 2,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:8548115fcae6ae84",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T03:28:04Z",
      "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": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1205.2540746232235,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.0096350455345,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 87,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:06Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1138.6513341974915,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 19.894443832996753,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-5-4-mini:8b748b4207b1c84c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T01:46:38Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1132.1434855724015,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 18.37810686686219,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 2,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:qwen-qwen3-7-plus:c57dfba2bd8782fc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 50,
      "max_score": null,
      "measured_at": "2026-08-04T01:12:37Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1126.7838784610865,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.815282073084678,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 2,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 210,
      "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": 77,
      "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": 168,
      "max_score": null,
      "measured_at": "2026-09-10T10:38:55Z",
      "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": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1092.582795701611,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 16.743097937091278,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 56,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:google-gemini-3-1-flash-lite:890697e687a48241",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T03:28:34Z",
      "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": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1094.6976995498242,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 14.799632473606307,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 109,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:44Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1027.8258491263755,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.662022800175135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 278,
      "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": 101,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:03Z",
      "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": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 2037.1859548088862,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 89.21089685186311,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 258
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 61,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-09-10T10:09:21Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1902.679336383488,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 75.68630623327066,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 61,
      "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": 31,
      "max_score": null,
      "measured_at": "2026-09-10T10:15:30Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1842.870478313909,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 70.16961646402447,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 276,
      "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": 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": "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": 68,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:35Z",
      "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": 276,
      "rating_method": "sequential_elo",
      "raw_elo": 1825.4782335252758,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 69.67529740665044,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 206,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-6-sol:34bccf96d771d2e5",
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "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-5.6-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": 49,
      "max_score": null,
      "measured_at": "2026-09-10T10:05:49Z",
      "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": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1802.802960584029,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 67.23618180536194,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:qwen-qwen3-8-2-4t-a95b:2caf8bc899f551f3",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": "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": 36,
      "max_score": null,
      "measured_at": "2026-09-10T10:05:31Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1782.8322402319461,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 64.6317689865653,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 61,
      "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": 43,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:03Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1757.519707353812,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 62.29697451515008,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:thinkingmachines-inkling:70a9ac993f011430",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "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": "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": 27,
      "max_score": null,
      "measured_at": "2026-08-05T03:33:08Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1745.1879860541585,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 60.57535339573391,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:claude-opus-4-8:6a24675422272c49",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 17,
      "max_score": null,
      "measured_at": "2026-08-03T04:47:27Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1751.2546865112345,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 60.46952997771049,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 47
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 356,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:claude-opus-5:e9ebdf808117b870",
      "capped_draws": 39,
      "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": "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": 88,
      "max_score": null,
      "measured_at": "2026-09-10T10:00:20Z",
      "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": 356,
      "rating_method": "sequential_elo",
      "raw_elo": 1700.9563586930085,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 57.326164470494916,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.624947000159003,
      "unilateral_faults": 0,
      "wins": 229
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:claude-opus-4-5:11b2bcd9aa32f256",
      "capped_draws": 3,
      "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": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 18,
      "max_score": null,
      "measured_at": "2026-08-03T01:17:19Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1644.8221338731084,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.580259976688616,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:meta-muse-spark-1-2:772fc6bb6f83c6c9",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 89,
      "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": "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": 124,
      "max_score": null,
      "measured_at": "2026-09-10T07:15:22Z",
      "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": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1600.6634489201153,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.684810281393695,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:google-gemini-3-8-flash:bf006bcd6ccb81c6",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-09-10T11:11:52Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1585.921427724455,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.49569805612314,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:minimax-minimax-m3:ce3665e0f9c1f1b1",
      "capped_draws": 3,
      "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": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 39,
      "max_score": null,
      "measured_at": "2026-08-02T23:32:13Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.3473690224341,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.98498009514775,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:z-ai-glm-5-2:51bd53334ebd6ddf",
      "capped_draws": 142,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 115,
      "draws": 142,
      "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": 42,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:45Z",
      "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": 1479.360612063329,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.79025072377557,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 12.848413703846715,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:claude-sonnet-5:5d48f6168d64e7fe",
      "capped_draws": 95,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 94,
      "draws": 95,
      "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": 94,
      "max_score": null,
      "measured_at": "2026-09-10T10:05:51Z",
      "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": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.9730792715607,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.35038166239203,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 194,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:qwen-qwen3-8-max:3a653d034173d2f2",
      "capped_draws": 89,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 90,
      "draws": 89,
      "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": 63,
      "max_score": null,
      "measured_at": "2026-09-10T04:18:48Z",
      "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": 194,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.3600386399553,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.11078030295988,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 138,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-4-nano:2d8b3620ce9c297f",
      "capped_draws": 69,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 68,
      "draws": 69,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:41:31Z",
      "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": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.7535435217649,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.88890946117016,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 16.804373924048683,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-6-terra:9663b021bc677328",
      "capped_draws": 77,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "draws": 77,
      "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": 58,
      "max_score": null,
      "measured_at": "2026-09-10T06:36:57Z",
      "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": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.233951031026,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.98624406261454,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:8548115fcae6ae84",
      "capped_draws": 60,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "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": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T02:32:37Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.3367882425214,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.42192058328905,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:google-gemma-4-31b-it:a05cbdb73d0f0757",
      "capped_draws": 66,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 19,
      "max_score": null,
      "measured_at": "2026-08-04T22:07:22Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.1732099119702,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.33433076646184,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-5:8d8c6268a221d9ee",
      "capped_draws": 62,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 62,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:22:27Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.2522873931011,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.245278775905984,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:tencent-hy3-preview:e682bc091589ac52",
      "capped_draws": 67,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 67,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:32:28Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.684392050828,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.240220004237862,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:nex-agi-nex-n2-pro:66b75a517d8692bb",
      "capped_draws": 72,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 72,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 10,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:06Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.2008821131521,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.091127162093525,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-4-1:fccd725c87f1cbd8",
      "capped_draws": 64,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "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-4.1",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 15,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:31Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.5680581389895,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.845909406584692,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-4-mini:8b748b4207b1c84c",
      "capped_draws": 50,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 50,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T06:58:48Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.8326222252044,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.27409368559002,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 2,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 142,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:x-ai-grok-4-6:f1d4c61e0708aeae",
      "capped_draws": 102,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 71,
      "draws": 102,
      "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": 31,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:41Z",
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1393.8371725931713,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.992778000535424,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:cohere-north-mini-code:bf20f7708e3f608c",
      "capped_draws": 72,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 72,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 20,
      "max_score": null,
      "measured_at": "2026-08-05T03:33:08Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.0183446522383,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.71763057558737,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:deepseek-deepseek-v4-pro:ff3e59d607a4ac18",
      "capped_draws": 119,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 119,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-09-10T05:37:11Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1385.5002735328487,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.13369122148454,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 180,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:meituan-longcat-2-0:8409ccd1edce8105",
      "capped_draws": 154,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 84,
      "draws": 154,
      "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": 21,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:06Z",
      "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": 180,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.4561955324614,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.9901170337506,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.673739368419632,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 186,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:poolside-laguna-s-2-1:834cbfa8b37e299a",
      "capped_draws": 151,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 87,
      "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": "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": 29,
      "max_score": null,
      "measured_at": "2026-08-05T05:33:39Z",
      "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": 186,
      "rating_method": "sequential_elo",
      "raw_elo": 1388.7043408168872,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.79904792639838,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.823251170389485,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:tencent-hy4-preview:9b637fbe1929d4b6",
      "capped_draws": 117,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "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": "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": 9,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:01Z",
      "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": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1375.432587894814,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.25108478892449,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:qwen-qwen3-8-flash:2ed602cefebb326c",
      "capped_draws": 120,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 120,
      "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": 7,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:45Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1373.0820244530325,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.964461868477382,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 136,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:meta-muse-spark-1-3:b665bb24258fc911",
      "capped_draws": 118,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 68,
      "draws": 118,
      "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": 6,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:51Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1371.8084535422936,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.894039629592516,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:inclusionai-ling-3-0-flash:fde230dc0f90d703",
      "capped_draws": 206,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 91,
      "draws": 206,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 35,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:59Z",
      "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": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1371.8937477883032,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.740061200441602,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.1611854626755758,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:qwen-qwen3-7-max:7378b9f3cb87014a",
      "capped_draws": 56,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "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": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 29,
      "max_score": null,
      "measured_at": "2026-08-05T05:33:39Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1377.4330339898045,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.609426626585595,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 638,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:google-gemini-3-6-flash:497c5e32f5a0da50",
      "capped_draws": 437,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 223,
      "draws": 437,
      "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": 159,
      "max_score": null,
      "measured_at": "2026-09-10T04:50:58Z",
      "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": 638,
      "rating_method": "sequential_elo",
      "raw_elo": 1356.0600605839268,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.519487645498753,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 148,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:thinkingmachines-inkling-small:2a1c609d5f09a424",
      "capped_draws": 131,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "draws": 131,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-09-10T04:15:56Z",
      "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": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1360.8178075609835,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.00987507357398,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 588,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:google-gemini-3-5-flash-lite:d8ea2a1333ff0452",
      "capped_draws": 438,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 198,
      "draws": 438,
      "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": 126,
      "max_score": null,
      "measured_at": "2026-09-10T11:10:23Z",
      "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": 588,
      "rating_method": "sequential_elo",
      "raw_elo": 1350.9578409877,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.974528845713063,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 126,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:google-gemini-3-5-flash:8f1504913d7602c4",
      "capped_draws": 111,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "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",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-09-10T11:08:37Z",
      "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": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1358.2869226844339,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.52508073799289,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:bytedance-seed-seed-2-0-code:95b26b11b0986534",
      "capped_draws": 116,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 116,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:39Z",
      "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": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1356.9501384467774,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.40177753232075,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 229,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-4:86f20e721b83e093",
      "capped_draws": 150,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 87,
      "draws": 150,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:11Z",
      "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": 229,
      "rating_method": "sequential_elo",
      "raw_elo": 1344.405660747203,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.08581983351418,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:deepseek-deepseek-v4-pro-0813:62f039a975dbbc18",
      "capped_draws": 109,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": "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": 6,
      "max_score": null,
      "measured_at": "2026-09-10T11:04:53Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1353.4712157354127,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.054798702264524,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 134,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:xiaomi-mimo-v2-5:a7d613e15ebacf2f",
      "capped_draws": 92,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 67,
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 40,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:45Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1362.1578754262378,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.67857257734565,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 16.928225102148446,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 284,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:o3:647217df3b12bb67",
      "capped_draws": 208,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 208,
      "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": 64,
      "max_score": null,
      "measured_at": "2026-09-10T07:32:27Z",
      "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": 284,
      "rating_method": "sequential_elo",
      "raw_elo": 1336.0753658355584,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.564760696036405,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:deepseek-deepseek-v4-flash:b05f493f9c8d196b",
      "capped_draws": 81,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": "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": 32,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:06Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1347.1953188706636,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.475918296517147,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:qwen-qwen3-8-27b:4712c07305d96aee",
      "capped_draws": 101,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": "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": 16,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:09Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1346.2937799317099,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.392761540116325,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:stealth-ox-alpha:2a6c37bfc1ea9a10",
      "capped_draws": 213,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 124,
      "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": "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": 28,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:20Z",
      "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": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1345.8798117191247,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.354577661057732,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:meta-muse-glimmer-30b:5f799292ad06c854",
      "capped_draws": 112,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": "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": 5,
      "max_score": null,
      "measured_at": "2026-09-10T11:05:42Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1341.382151499178,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.93971944570675,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:openai-gpt-oss-120b:e4864d083f4798c2",
      "capped_draws": 112,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": "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": 12,
      "max_score": null,
      "measured_at": "2026-09-10T11:05:48Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1314.8381985720714,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 21.491340421683823,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:stepfun-step-3-7-flash:283efeb922617cca",
      "capped_draws": 192,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 96,
      "draws": 192,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:38Z",
      "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": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1296.7353446789812,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.829015374383967,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:z-ai-glm-5-3:d95da7acd9780380",
      "capped_draws": 86,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": "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": 38,
      "max_score": null,
      "measured_at": "2026-09-10T11:09:46Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1286.0804835275962,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 18.83876691512749,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:z-ai-glm-5-3-flash:1c774d2a8faa3025",
      "capped_draws": 81,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 81,
      "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": 40,
      "max_score": null,
      "measured_at": "2026-09-10T11:08:42Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1231.9861064630934,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 13.849173297099911,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 206,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-6-luna:1c8c41335b2357b1",
      "capped_draws": 41,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "draws": 41,
      "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": 153,
      "max_score": null,
      "measured_at": "2026-09-10T10:00:52Z",
      "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": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1073.865967034946,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 11,
      "attempted_matches": 1322,
      "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
        },
        "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": 92.37884458659907,
      "contributing_entrants": null,
      "distinct_rated_opponents": 42,
      "draws": 46,
      "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": "2026-09-10T11:06:04Z",
      "losses": 95,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 76.96244740112121,
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1322,
      "rating_method": "sequential_elo",
      "raw_elo": 2008.213355474128,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 92.37884458659907,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 8,
      "attempted_matches": 952,
      "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
        },
        "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": 10.427439999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 90.95955634051866,
      "contributing_entrants": null,
      "distinct_rated_opponents": 40,
      "draws": 35,
      "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": "2026-09-10T11:06:16Z",
      "losses": 60,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 68.46930350710791,
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 952,
      "rating_method": "sequential_elo",
      "raw_elo": 1984.8202093607915,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 90.95955634051866,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 857
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1595,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-5-6-sol:c051d828081d0d91",
      "capped_draws": 7,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "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": 75.3716089885212,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 112,
      "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": "2026-09-10T11:11:42Z",
      "losses": 314,
      "max_score": 95.50333681723484,
      "measured_at": null,
      "min_score": 57.6005678523054,
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1594,
      "rating_method": "sequential_elo",
      "raw_elo": 1828.5320119233652,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 75.3716089885212,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1168
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1474,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-5-4:6f2d7de576c6f541",
      "capped_draws": 40,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "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": 65.15382836806302,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 227,
      "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": "2026-09-10T11:09:05Z",
      "losses": 321,
      "max_score": 91.89049593436994,
      "measured_at": null,
      "min_score": 26.86648580703239,
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1468,
      "rating_method": "sequential_elo",
      "raw_elo": 1764.7594151715166,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 63.01471156610657,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 920
    },
    {
      "admitted_plugins": 13,
      "attempted_matches": 626,
      "canonical_public_row_identity": "publication-row.v1:intensive:claude-opus-5:9f8812658c6b6343",
      "capped_draws": 1,
      "codegen_cost_usd": {
        "admitted_cell_count": 13,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 16
        },
        "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": 64.24813629810149,
      "contributing_entrants": null,
      "distinct_rated_opponents": 26,
      "draws": 40,
      "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": "2026-08-05T04:44:12Z",
      "losses": 115,
      "max_score": 85.05036844756516,
      "measured_at": null,
      "min_score": 42.027298685176675,
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 626,
      "rating_method": "sequential_elo",
      "raw_elo": 1771.0674028137453,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 60.99810969744108,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 8,
      "attempted_matches": 978,
      "canonical_public_row_identity": "publication-row.v1:intensive:claude-fable-5:f2454da3451cc4f4",
      "capped_draws": 60,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "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": 59.95385418281583,
      "contributing_entrants": null,
      "distinct_rated_opponents": 41,
      "draws": 169,
      "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": "2026-09-10T11:00:18Z",
      "losses": 289,
      "max_score": 85.88512253636422,
      "measured_at": null,
      "min_score": 37.59961008402652,
      "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": 972,
      "rating_method": "sequential_elo",
      "raw_elo": 1697.438766010291,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 59.95385418281583,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 514
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 425,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-5-5:df705e696fe9cc4f",
      "capped_draws": 31,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "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": 59.0535146259817,
      "contributing_entrants": null,
      "distinct_rated_opponents": 30,
      "draws": 80,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "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": "2026-08-05T04:35:52Z",
      "losses": 92,
      "max_score": 82.05925729033785,
      "measured_at": null,
      "min_score": 17.140349376902293,
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 424,
      "rating_method": "sequential_elo",
      "raw_elo": 1724.6113224164167,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 57.11468204292295,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 252
    },
    {
      "admitted_plugins": 25,
      "attempted_matches": 3255,
      "canonical_public_row_identity": "publication-row.v1:intensive:stealth-ox-alpha:650c74dfce556ee1",
      "capped_draws": 74,
      "codegen_cost_usd": {
        "admitted_cell_count": 25,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 31
        },
        "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": 56.86801757531599,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 474,
      "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": "2026-09-10T11:09:55Z",
      "losses": 1116,
      "max_score": 63.32717677815119,
      "measured_at": null,
      "min_score": 47.83064684889641,
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3118,
      "rating_method": "sequential_elo",
      "raw_elo": 1647.1457974188295,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 56.86801757531599,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 131,
      "wins": 1528
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 446,
      "canonical_public_row_identity": "publication-row.v1:intensive:claude-opus-4-8:47e9dafb56058af5",
      "capped_draws": 13,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 9
        },
        "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": 58.213545390771856,
      "contributing_entrants": null,
      "distinct_rated_opponents": 31,
      "draws": 56,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "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": "2026-08-05T03:23:19Z",
      "losses": 115,
      "max_score": 70.79490986212144,
      "measured_at": null,
      "min_score": 48.94611757043748,
      "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": 446,
      "rating_method": "sequential_elo",
      "raw_elo": 1680.8148115126678,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 56.302290501137556,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 275
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1034,
      "canonical_public_row_identity": "publication-row.v1:intensive:tencent-hy4-preview:aa03f826bc323244",
      "capped_draws": 203,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "evidence_basis": "Provider-reported",
        "max": 0.151385561,
        "mean": 0.12117269062500001,
        "median": 0.1216224665,
        "min": 0.099918984,
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.969381525
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 54.78773402205262,
      "contributing_entrants": null,
      "distinct_rated_opponents": 42,
      "draws": 310,
      "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": "2026-09-10T11:05:01Z",
      "losses": 317,
      "max_score": 73.34304806796328,
      "measured_at": null,
      "min_score": 27.68709794444988,
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1028,
      "rating_method": "sequential_elo",
      "raw_elo": 1634.0101861421667,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 54.78773402205262,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 401
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1015,
      "canonical_public_row_identity": "publication-row.v1:intensive:qwen-qwen3-8-2-4t-a95b:80d9bb5405a8b814",
      "capped_draws": 53,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 10
        },
        "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": 53.26667306538265,
      "contributing_entrants": null,
      "distinct_rated_opponents": 42,
      "draws": 267,
      "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": "2026-09-10T11:11:56Z",
      "losses": 312,
      "max_score": 85.08829766988379,
      "measured_at": null,
      "min_score": 29.297101237978474,
      "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": 1009,
      "rating_method": "sequential_elo",
      "raw_elo": 1646.398092070077,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 53.26667306538265,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 430
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1084,
      "canonical_public_row_identity": "publication-row.v1:intensive:x-ai-grok-4-6:5c921eacd53762a9",
      "capped_draws": 99,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "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": 53.08560240806504,
      "contributing_entrants": null,
      "distinct_rated_opponents": 41,
      "draws": 242,
      "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": "2026-09-10T11:09:42Z",
      "losses": 371,
      "max_score": 82.4874985834472,
      "measured_at": null,
      "min_score": 23.843971005685763,
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1084,
      "rating_method": "sequential_elo",
      "raw_elo": 1631.618956826306,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 53.08560240806504,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 8,
      "attempted_matches": 992,
      "canonical_public_row_identity": "publication-row.v1:intensive:google-gemini-3-8-flash:7ef3571107626567",
      "capped_draws": 51,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 9
        },
        "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": 52.4147765736809,
      "contributing_entrants": null,
      "distinct_rated_opponents": 41,
      "draws": 149,
      "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": "2026-09-10T11:00:26Z",
      "losses": 421,
      "max_score": 79.59975068636147,
      "measured_at": null,
      "min_score": 35.81130147891559,
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 991,
      "rating_method": "sequential_elo",
      "raw_elo": 1627.3108629141504,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 52.4147765736809,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 421
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 3029,
      "canonical_public_row_identity": "publication-row.v1:intensive:google-gemini-3-6-flash:1efb2291cbf800fd",
      "capped_draws": 390,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 53
        },
        "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": 55.68219526351658,
      "contributing_entrants": null,
      "distinct_rated_opponents": 50,
      "draws": 566,
      "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": "2026-09-10T11:10:23Z",
      "losses": 885,
      "max_score": 85.6020891745296,
      "measured_at": null,
      "min_score": 38.850120833000595,
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3023,
      "rating_method": "sequential_elo",
      "raw_elo": 1640.8133672735662,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 51.818121477700444,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 1572
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2144,
      "canonical_public_row_identity": "publication-row.v1:intensive:x-ai-grok-4-5:b0a92c183e177d45",
      "capped_draws": 82,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "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": 51.6937015030495,
      "contributing_entrants": null,
      "distinct_rated_opponents": 50,
      "draws": 407,
      "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": "2026-09-10T10:53:15Z",
      "losses": 599,
      "max_score": 81.02581011754175,
      "measured_at": null,
      "min_score": 14.194010354631436,
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2144,
      "rating_method": "sequential_elo",
      "raw_elo": 1628.8388345128037,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 51.6937015030495,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1138
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 958,
      "canonical_public_row_identity": "publication-row.v1:intensive:z-ai-glm-5-3-flash:cea57e181d1e302f",
      "capped_draws": 113,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "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": 49.69482600982666,
      "contributing_entrants": null,
      "distinct_rated_opponents": 42,
      "draws": 232,
      "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": "2026-09-10T11:06:10Z",
      "losses": 348,
      "max_score": 71.64471752845151,
      "measured_at": null,
      "min_score": 17.540748548543018,
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 958,
      "rating_method": "sequential_elo",
      "raw_elo": 1558.9694711820664,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 49.69482600982666,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 8,
      "attempted_matches": 1022,
      "canonical_public_row_identity": "publication-row.v1:intensive:google-gemini-3-5-flash:27c90777b8ed242d",
      "capped_draws": 58,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 11
        },
        "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": 48.242638257789736,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 230,
      "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": "2026-09-10T10:48:35Z",
      "losses": 378,
      "max_score": 82.02311872112153,
      "measured_at": null,
      "min_score": 19.436408028603687,
      "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": 1022,
      "rating_method": "sequential_elo",
      "raw_elo": 1603.15565731743,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 48.242638257789736,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 414
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 767,
      "canonical_public_row_identity": "publication-row.v1:intensive:qwen-qwen3-8-27b:a0a78367379103f7",
      "capped_draws": 64,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "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": 50.590074067871484,
      "contributing_entrants": null,
      "distinct_rated_opponents": 42,
      "draws": 107,
      "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": "2026-09-10T11:11:13Z",
      "losses": 316,
      "max_score": 74.97439218948013,
      "measured_at": null,
      "min_score": 29.853834414688254,
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 767,
      "rating_method": "sequential_elo",
      "raw_elo": 1558.5319824190376,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 47.079368749896325,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 344
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1686,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-5-6-luna:0e3f3e6646cbf8db",
      "capped_draws": 172,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "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": 45.30312374197206,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 576,
      "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": "2026-09-10T11:08:37Z",
      "losses": 458,
      "max_score": 79.12179151899733,
      "measured_at": null,
      "min_score": 10.237515749847217,
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1682,
      "rating_method": "sequential_elo",
      "raw_elo": 1583.0255194022957,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 45.30312374197206,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 648
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1658,
      "canonical_public_row_identity": "publication-row.v1:intensive:claude-sonnet-5:4c96a5e86d12d58b",
      "capped_draws": 32,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "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": 43.54754891745874,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 376,
      "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": "2026-09-10T10:25:59Z",
      "losses": 619,
      "max_score": 74.33339438299416,
      "measured_at": null,
      "min_score": 7.484704864315055,
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1657,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.1533988456465,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 43.54754891745874,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 662
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1074,
      "canonical_public_row_identity": "publication-row.v1:intensive:deepseek-deepseek-v4-pro-0813:980c9c0ee71edcf8",
      "capped_draws": 107,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "evidence_basis": "Provider-reported",
        "max": 0.28337826924,
        "mean": 0.14657020603499998,
        "median": 0.140081106,
        "min": 0.07036986,
        "recorded_attempt_count": 10,
        "run_count": 8,
        "total": 1.17256164828
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 41.37071157031049,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 333,
      "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": "2026-09-10T11:09:39Z",
      "losses": 334,
      "max_score": 74.8155896456324,
      "measured_at": null,
      "min_score": 9.963827021369582,
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1074,
      "rating_method": "sequential_elo",
      "raw_elo": 1530.5882675031414,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 41.37071157031049,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 407
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 515,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-5:fa08b5a89f0aa0b3",
      "capped_draws": 57,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "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": 2.2561125
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.5842067414882,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 165,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": "2026-08-05T05:05:23Z",
      "losses": 176,
      "max_score": 65.51337979360243,
      "measured_at": null,
      "min_score": 12.515897799774466,
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 514,
      "rating_method": "sequential_elo",
      "raw_elo": 1538.8348441013682,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 40.5842067414882,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 173
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1121,
      "canonical_public_row_identity": "publication-row.v1:intensive:qwen-qwen3-8-max:83f392701e202fd4",
      "capped_draws": 131,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "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": 42.05605079183701,
      "contributing_entrants": null,
      "distinct_rated_opponents": 42,
      "draws": 305,
      "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": "2026-09-10T11:11:37Z",
      "losses": 420,
      "max_score": 73.66211615758745,
      "measured_at": null,
      "min_score": 22.390163615050678,
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1121,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.948054319958,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 39.77415714419122,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 396
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1100,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-5-6-terra:7c2a658c6918f6e6",
      "capped_draws": 98,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "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": 39.668834509119144,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 326,
      "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": "2026-09-10T10:37:07Z",
      "losses": 380,
      "max_score": 69.43940999034174,
      "measured_at": null,
      "min_score": 17.367291620527613,
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1100,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.3727889411705,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 39.668834509119144,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 394
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1065,
      "canonical_public_row_identity": "publication-row.v1:intensive:deepseek-deepseek-v4-pro:91e0c8a35047bbc6",
      "capped_draws": 121,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "evidence_basis": "Provider-reported",
        "max": 0.176790095,
        "mean": 0.114196574281125,
        "median": 0.09418628700000001,
        "min": 0.06074422244,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.913572594249
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.9734452809923,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 348,
      "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": "2026-09-10T11:11:38Z",
      "losses": 388,
      "max_score": 70.6332524935784,
      "measured_at": null,
      "min_score": 10.858956125600434,
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1065,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.8987740716207,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 38.9734452809923,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 329
    },
    {
      "admitted_plugins": 19,
      "attempted_matches": 5128,
      "canonical_public_row_identity": "publication-row.v1:intensive:o3:908e4e2cf254357c",
      "capped_draws": 472,
      "codegen_cost_usd": {
        "admitted_cell_count": 19,
        "cell_count": 8,
        "cost_basis_counts": {
          "estimated": 32,
          "local_standard_estimate": 8
        },
        "evidence_basis": "Combined: Recorded attempt + Standard list-price estimate",
        "failed_cell_count": 13,
        "max": 0.1097735,
        "mean": 0.091486,
        "median": 0.08840575,
        "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": 42.65797926498379,
      "contributing_entrants": null,
      "distinct_rated_opponents": 50,
      "draws": 590,
      "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": "2026-09-10T11:10:18Z",
      "losses": 2264,
      "max_score": 49.93788221593318,
      "measured_at": null,
      "min_score": 31.45724153790146,
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 5128,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.7485661098071,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 37.44563368460245,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 2274
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 444,
      "canonical_public_row_identity": "publication-row.v1:intensive:tencent-hy3-preview:39292dc0f6c6c917",
      "capped_draws": 37,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "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": 34.085726250217604,
      "contributing_entrants": null,
      "distinct_rated_opponents": 32,
      "draws": 116,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "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": "2026-08-05T05:11:51Z",
      "losses": 187,
      "max_score": 58.73748205542807,
      "measured_at": null,
      "min_score": 7.834028495391087,
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 442,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.3610026683039,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 32.010056035752946,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 139
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 339,
      "canonical_public_row_identity": "publication-row.v1:intensive:stepfun-step-3-7-flash:4d7c266d9504ba14",
      "capped_draws": 52,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 20
        },
        "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": 35.767705313356814,
      "contributing_entrants": null,
      "distinct_rated_opponents": 31,
      "draws": 54,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "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": "2026-08-05T03:50:20Z",
      "losses": 167,
      "max_score": 45.69828843610223,
      "measured_at": null,
      "min_score": 17.73358084856714,
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 339,
      "rating_method": "sequential_elo",
      "raw_elo": 1389.2684513348431,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 31.8024869515411,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 118
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1038,
      "canonical_public_row_identity": "publication-row.v1:intensive:z-ai-glm-5-2:d977e6638f849d00",
      "capped_draws": 176,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "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": 30.60405657846155,
      "contributing_entrants": null,
      "distinct_rated_opponents": 42,
      "draws": 335,
      "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": "2026-09-10T11:06:11Z",
      "losses": 444,
      "max_score": 54.56042710751232,
      "measured_at": null,
      "min_score": 3.385411727320254,
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1038,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.8841136861088,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 30.60405657846155,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 259
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1078,
      "canonical_public_row_identity": "publication-row.v1:intensive:bytedance-seed-seed-2-0-code:87a10b251e401fd3",
      "capped_draws": 142,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "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": 30.297799008678222,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "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": "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": "2026-09-10T11:08:48Z",
      "losses": 391,
      "max_score": 49.72447731658255,
      "measured_at": null,
      "min_score": 7.518607942495322,
      "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": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1075,
      "rating_method": "sequential_elo",
      "raw_elo": 1401.9307916720434,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 30.297799008678222,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 307
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 872,
      "canonical_public_row_identity": "publication-row.v1:intensive:deepseek-deepseek-v4-flash:bd0b950926bd00a0",
      "capped_draws": 154,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "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": 30.607605316675038,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 380,
      "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": "2026-09-10T10:03:50Z",
      "losses": 273,
      "max_score": 73.77217005426371,
      "measured_at": null,
      "min_score": 2.2211281793648086,
      "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": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 872,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.6018854928745,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 29.60270285061144,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 219
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 898,
      "canonical_public_row_identity": "publication-row.v1:intensive:meta-muse-glimmer-30b:b931921706d77dd0",
      "capped_draws": 177,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "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": 29.80850611716221,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 410,
      "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": "2026-09-10T11:07:30Z",
      "losses": 266,
      "max_score": 49.03370945933072,
      "measured_at": null,
      "min_score": 8.569180028204126,
      "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": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 898,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.7481350106614,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 28.829839508099237,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 222
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1123,
      "canonical_public_row_identity": "publication-row.v1:intensive:thinkingmachines-inkling-small:bbca5c562fb1ab46",
      "capped_draws": 170,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "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": 0.38761485
      },
      "codegen_evaluated_cells": 10,
      "conditional_success_score": 30.174245478812885,
      "contributing_entrants": null,
      "distinct_rated_opponents": 42,
      "draws": 426,
      "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": "2026-09-10T10:55:16Z",
      "losses": 362,
      "max_score": 49.240345149208736,
      "measured_at": null,
      "min_score": 10.341010847452775,
      "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": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1123,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.566408918735,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 28.537039469589303,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 335
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 349,
      "canonical_public_row_identity": "publication-row.v1:intensive:google-gemini-3-1-flash-lite:acd1e78007489bf4",
      "capped_draws": 54,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "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": 31.10122013544669,
      "contributing_entrants": null,
      "distinct_rated_opponents": 32,
      "draws": 101,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "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": "2026-08-05T05:05:18Z",
      "losses": 179,
      "max_score": 45.56327909407335,
      "measured_at": null,
      "min_score": 24.238563997706606,
      "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": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 349,
      "rating_method": "sequential_elo",
      "raw_elo": 1364.6887064246337,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 27.653329696976403,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 3294,
      "canonical_public_row_identity": "publication-row.v1:intensive:google-gemini-3-5-flash-lite:abb2b9fa09f58cba",
      "capped_draws": 274,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 50
        },
        "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": 28.216737067230966,
      "contributing_entrants": null,
      "distinct_rated_opponents": 50,
      "draws": 883,
      "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": "2026-09-10T11:08:35Z",
      "losses": 1385,
      "max_score": 48.1277645295087,
      "measured_at": null,
      "min_score": 12.3621226468018,
      "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": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3292,
      "rating_method": "sequential_elo",
      "raw_elo": 1367.6718240595555,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 27.290331085130802,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1024
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 908,
      "canonical_public_row_identity": "publication-row.v1:intensive:openai-gpt-oss-120b:e79c900fda7b779f",
      "capped_draws": 130,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "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": 27.433152416942608,
      "contributing_entrants": null,
      "distinct_rated_opponents": 42,
      "draws": 386,
      "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": "2026-09-10T10:49:44Z",
      "losses": 305,
      "max_score": 53.690628075980555,
      "measured_at": null,
      "min_score": 12.913154477319852,
      "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": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 907,
      "rating_method": "sequential_elo",
      "raw_elo": 1373.725766506921,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 26.532472921423064,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 216
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 282,
      "canonical_public_row_identity": "publication-row.v1:intensive:xiaomi-mimo-v2-5:b10f89265c5b1dcb",
      "capped_draws": 92,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "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": 29.66033164309214,
      "contributing_entrants": null,
      "distinct_rated_opponents": 31,
      "draws": 178,
      "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": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "2026-07-31T20:22:54Z",
      "losses": 63,
      "max_score": 55.88030293196678,
      "measured_at": null,
      "min_score": 14.876831236011256,
      "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": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 282,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.0182986919922,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 26.37217852791834,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 9,
      "attempted_matches": 573,
      "canonical_public_row_identity": "publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:592235e55055263e",
      "capped_draws": 115,
      "codegen_cost_usd": {
        "admitted_cell_count": 9,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 35
        },
        "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": 30.26933128936782,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 252,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "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": "2026-08-05T04:29:54Z",
      "losses": 196,
      "max_score": 47.23542996577578,
      "measured_at": null,
      "min_score": 11.68296478061394,
      "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": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 573,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.6288767387816,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 26.21400985215971,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 125
    },
    {
      "admitted_plugins": 9,
      "attempted_matches": 2368,
      "canonical_public_row_identity": "publication-row.v1:intensive:thinkingmachines-inkling:8db7573c02acc990",
      "capped_draws": 303,
      "codegen_cost_usd": {
        "admitted_cell_count": 9,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 53
        },
        "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": 26.43318592739723,
      "contributing_entrants": null,
      "distinct_rated_opponents": 50,
      "draws": 773,
      "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": "2026-09-10T11:08:22Z",
      "losses": 1108,
      "max_score": 55.3334397747058,
      "measured_at": null,
      "min_score": 9.050334687326071,
      "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": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2366,
      "rating_method": "sequential_elo",
      "raw_elo": 1340.9913264100708,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 22.891810516083325,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 485
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 718,
      "canonical_public_row_identity": "publication-row.v1:intensive:inception-mercury-2-5-preview:e936b6bbd630c36b",
      "capped_draws": 130,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "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": 17.46211413058019,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 323,
      "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": "2026-09-10T11:05:37Z",
      "losses": 317,
      "max_score": 24.270432377976235,
      "measured_at": null,
      "min_score": 10.683228762592293,
      "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": 40,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 718,
      "rating_method": "sequential_elo",
      "raw_elo": 1259.6489304042077,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 16.25032826011336,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 844,
      "canonical_public_row_identity": "publication-row.v1:intensive:z-ai-glm-5-3:e8ce4aed95c7494d",
      "capped_draws": 10,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "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": 78.85594773673789,
      "contributing_entrants": null,
      "distinct_rated_opponents": 40,
      "draws": 101,
      "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": "2026-09-10T11:05:19Z",
      "losses": 112,
      "max_score": 98.77394998739801,
      "measured_at": null,
      "min_score": 35.48069279237866,
      "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": 838,
      "rating_method": "sequential_elo",
      "raw_elo": 1928.1620525983792,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 78.85594773673789,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 625
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 724,
      "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
        },
        "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": 54.944564738186564,
      "contributing_entrants": null,
      "distinct_rated_opponents": 41,
      "draws": 131,
      "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": "2026-09-10T11:11:14Z",
      "losses": 252,
      "max_score": 79.56504037106075,
      "measured_at": null,
      "min_score": 18.420844285465474,
      "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": 723,
      "rating_method": "sequential_elo",
      "raw_elo": 1679.467858899104,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 54.944564738186564,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 340
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 420,
      "canonical_public_row_identity": "publication-row.v1:intensive:meta-muse-spark-1-2:8ed12b9970d2209b",
      "capped_draws": 33,
      "codegen_cost_usd": {
        "admitted_cell_count": 2,
        "cell_count": 2,
        "cost_basis_counts": {
          "provider_reported": 2
        },
        "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": 43.05120520009523,
      "contributing_entrants": null,
      "distinct_rated_opponents": 40,
      "draws": 51,
      "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": "2026-09-10T11:05:40Z",
      "losses": 190,
      "max_score": 51.675962062161574,
      "measured_at": null,
      "min_score": 34.42644833802889,
      "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": 420,
      "rating_method": "sequential_elo",
      "raw_elo": 1524.937926280082,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 43.05120520009523,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 179
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 1314,
      "canonical_public_row_identity": "publication-row.v1:intensive:moonshotai-kimi-k3:6cfd7a6936cf4591",
      "capped_draws": 38,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "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": 4.208937
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 44.59194591921063,
      "contributing_entrants": null,
      "distinct_rated_opponents": 49,
      "draws": 413,
      "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": "2026-09-10T11:06:10Z",
      "losses": 419,
      "max_score": 65.77337510145159,
      "measured_at": null,
      "min_score": 13.442672880681176,
      "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": 1302,
      "rating_method": "sequential_elo",
      "raw_elo": 1555.769339523801,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 40.99438879961144,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 470
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2248,
      "canonical_public_row_identity": "publication-row.v1:intensive:claude-opus-4-5:0dacb4d5b9cf9367",
      "capped_draws": 247,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 17
        },
        "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": 35.14311845280274,
      "contributing_entrants": null,
      "distinct_rated_opponents": 51,
      "draws": 705,
      "eligibility_flag": false,
      "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": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-10T11:11:52Z",
      "losses": 809,
      "max_score": 54.54022332767149,
      "measured_at": null,
      "min_score": 4.775250900350241,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 2248,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.3209470524448,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 35.14311845280274,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 734
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "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
        },
        "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": 0.059244639999999994
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 20.32563417683313,
      "contributing_entrants": null,
      "distinct_rated_opponents": 30,
      "draws": 101,
      "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": "2026-09-10T11:00:35Z",
      "losses": 30,
      "max_score": 20.32563417683313,
      "measured_at": null,
      "min_score": 20.32563417683313,
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1328.441766750424,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "track",
      "score": 12.085694390016217,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 202,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:gpt-5-4:6f2d7de576c6f541",
      "capped_draws": 4,
      "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": "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": 11,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:09Z",
      "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": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 2082.5792261697334,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 91.89049593436994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 187
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:14Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 2056.7386464310007,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 89.05863634547586,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 113
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:google-gemini-3-5-flash:27c90777b8ed242d",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "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": "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": 18,
      "max_score": null,
      "measured_at": "2026-09-10T10:09:43Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1971.1902035562755,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 82.02311872112153,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:z-ai-glm-5-3:e8ce4aed95c7494d",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "draws": 10,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-09-10T10:10:04Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1940.1681080558346,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 79.47185662559322,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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": 26,
      "max_score": null,
      "measured_at": "2026-09-10T10:09:07Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1925.0620812038217,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 78.22953456127536,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-09-10T10:09:13Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1909.6549229355353,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 76.96244740112121,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 100
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 200,
      "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": 80,
      "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": 58,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:07Z",
      "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": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1883.3980174205028,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 75.49834308214069,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 142
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:x-ai-grok-4-5:b0a92c183e177d45",
      "capped_draws": 56,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 94,
      "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": "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": 31,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:31Z",
      "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": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1851.5695914706555,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 73.17261948899618,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 120,
      "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": 60,
      "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": 42,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:14Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1744.789818576751,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 63.4289408206194,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 119,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:qwen-qwen3-8-27b:a0a78367379103f7",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 4,
      "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": 54,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:13Z",
      "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": 119,
      "rating_method": "sequential_elo",
      "raw_elo": 1723.2392832402293,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 61.64418656956991,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.8935464587638418,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:gpt-5-5:df705e696fe9cc4f",
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 21,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:28:59Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1723.735552560467,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 60.47607649312432,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 203,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:gpt-5-6-sol:c051d828081d0d91",
      "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": "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": 80,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:42Z",
      "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": 203,
      "rating_method": "sequential_elo",
      "raw_elo": 1665.561627843407,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 57.6005678523054,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 278,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:moonshotai-kimi-k3:6cfd7a6936cf4591",
      "capped_draws": 29,
      "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": "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": 108,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:10Z",
      "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": 272,
      "rating_method": "sequential_elo",
      "raw_elo": 1640.1968317903131,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.82678776607858,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 243,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:claude-opus-4-5:0dacb4d5b9cf9367",
      "capped_draws": 39,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 89,
      "draws": 39,
      "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": 80,
      "max_score": null,
      "measured_at": "2026-09-10T11:05:01Z",
      "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": 243,
      "rating_method": "sequential_elo",
      "raw_elo": 1625.9511140533318,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.54022332767149,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 124
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:claude-opus-4-8:47e9dafb56058af5",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 13,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T21:47:36Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1628.124836644718,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 52.97475225210645,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:claude-opus-5:9f8812658c6b6343",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 45,
      "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",
        "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": 37,
      "max_score": null,
      "measured_at": "2026-08-03T14:42:13Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1632.891716608698,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 52.610603965911444,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 26.264004201400486,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 210,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:meta-muse-spark-1-2:8ed12b9970d2209b",
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "draws": 22,
      "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": 101,
      "max_score": null,
      "measured_at": "2026-09-10T11:05:40Z",
      "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": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1593.052861841246,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 51.675962062161574,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:x-ai-grok-4-6:5c921eacd53762a9",
      "capped_draws": 42,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 42,
      "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": 35,
      "max_score": null,
      "measured_at": "2026-09-10T11:09:42Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1595.6553927632428,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 51.1641017896463,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:tencent-hy3-preview:39292dc0f6c6c917",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "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": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T13:20:55Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1594.4036920144524,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.032819133002,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:z-ai-glm-5-3-flash:cea57e181d1e302f",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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-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": 63,
      "max_score": null,
      "measured_at": "2026-09-10T11:05:40Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1579.1908972997724,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.834472121274,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 164,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:tencent-hy4-preview:aa03f826bc323244",
      "capped_draws": 71,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "draws": 71,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-09-10T11:05:01Z",
      "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": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1553.627998089601,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.137358293252255,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:gpt-5-6-terra:7c2a658c6918f6e6",
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 24,
      "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": 43,
      "max_score": null,
      "measured_at": "2026-09-10T04:47:49Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1555.767687387719,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.93196838089745,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 380,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:stealth-ox-alpha:650c74dfce556ee1",
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 190,
      "draws": 21,
      "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": 176,
      "max_score": null,
      "measured_at": "2026-09-10T11:09:55Z",
      "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": 380,
      "rating_method": "sequential_elo",
      "raw_elo": 1554.229696147544,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.83064684889641,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.1363636363636391,
      "unilateral_faults": 0,
      "wins": 183
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 740,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:o3:908e4e2cf254357c",
      "capped_draws": 78,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 260,
      "draws": 78,
      "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": 298,
      "max_score": null,
      "measured_at": "2026-09-10T11:09:51Z",
      "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": 740,
      "rating_method": "sequential_elo",
      "raw_elo": 1542.8030567183832,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.71717706185117,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 364
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:gpt-5:fa08b5a89f0aa0b3",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 5,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:31:39Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.0545313969262,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.42515101914064,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 152,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:google-gemini-3-8-flash:7ef3571107626567",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 76,
      "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": "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": 89,
      "max_score": null,
      "measured_at": "2026-09-10T07:16:36Z",
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1524.210378608972,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.61951452356562,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 164,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:z-ai-glm-5-2:d977e6638f849d00",
      "capped_draws": 55,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "draws": 55,
      "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": 68,
      "max_score": null,
      "measured_at": "2026-09-10T11:05:49Z",
      "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": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.440886827866,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.243564635376174,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:claude-sonnet-5:4c96a5e86d12d58b",
      "capped_draws": 28,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 91,
      "draws": 28,
      "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": 108,
      "max_score": null,
      "measured_at": "2026-09-10T07:39:14Z",
      "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": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1506.4520159219408,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.70826959385252,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 106
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 517,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:google-gemini-3-6-flash:1efb2291cbf800fd",
      "capped_draws": 174,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 187,
      "draws": 174,
      "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": 179,
      "max_score": null,
      "measured_at": "2026-09-10T11:10:23Z",
      "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": 514,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.2581565241724,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.1763070086701,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 161
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 155,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:qwen-qwen3-8-2-4t-a95b:80d9bb5405a8b814",
      "capped_draws": 50,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 78,
      "draws": 50,
      "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": 38,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:56Z",
      "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": 155,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.4989415222879,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.44845781533551,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:592235e55055263e",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "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": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:16:49Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.5929703577895,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.81038879854182,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:deepseek-deepseek-v4-pro-0813:980c9c0ee71edcf8",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 4,
      "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": 48,
      "max_score": null,
      "measured_at": "2026-09-10T11:05:43Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1388.3076463525476,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.13620303413409,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:google-gemini-3-5-flash-lite:abb2b9fa09f58cba",
      "capped_draws": 57,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 83,
      "draws": 57,
      "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": 116,
      "max_score": null,
      "measured_at": "2026-09-10T11:08:35Z",
      "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": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1368.4377311620217,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.35795274164543,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:bytedance-seed-seed-2-0-code:87a10b251e401fd3",
      "capped_draws": 73,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 73,
      "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": 25,
      "max_score": null,
      "measured_at": "2026-09-10T11:08:48Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1364.7121364177256,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.19570452330597,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:meta-muse-glimmer-30b:b931921706d77dd0",
      "capped_draws": 54,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 54,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-09-10T11:07:30Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1331.2121180284705,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.440657653090735,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:thinkingmachines-inkling-small:bbca5c562fb1ab46",
      "capped_draws": 46,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 46,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-09-10T09:59:45Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1290.1434413527058,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.03875004306578,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:xiaomi-mimo-v2-5:b10f89265c5b1dcb",
      "capped_draws": 39,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "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": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 19,
      "max_score": null,
      "measured_at": "2026-07-31T00:39:03Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1277.5373789071825,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.780667328407972,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 121,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:deepseek-deepseek-v4-pro:91e0c8a35047bbc6",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 7,
      "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": 81,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:38Z",
      "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": 121,
      "rating_method": "sequential_elo",
      "raw_elo": 1262.4843318048977,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.77634202676228,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.5178730212592662,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 121,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:qwen-qwen3-8-max:83f392701e202fd4",
      "capped_draws": 32,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 32,
      "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": 60,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:37Z",
      "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": 121,
      "rating_method": "sequential_elo",
      "raw_elo": 1261.9654836736365,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.733671873464495,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.5178730212592662,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:inception-mercury-2-5-preview:e936b6bbd630c36b",
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": "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": 63,
      "max_score": null,
      "measured_at": "2026-09-10T09:58:35Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1257.0243633029106,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.315031767294062,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:stepfun-step-3-7-flash:4d7c266d9504ba14",
      "capped_draws": 6,
      "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": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:35:13Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1204.0077738517675,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.73358084856714,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:deepseek-deepseek-v4-flash:bd0b950926bd00a0",
      "capped_draws": 39,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 39,
      "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": 76,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:36Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1176.5212783168986,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 16.69444518264546,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:thinkingmachines-inkling:8db7573c02acc990",
      "capped_draws": 95,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 83,
      "draws": 95,
      "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": 139,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:12Z",
      "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": 1148.0712009628478,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 15.234974053366383,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 104,
      "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": 52,
      "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-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": 5,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:04Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1947.6719384807805,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 94
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 5,
      "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": "2026-09-10T10:26:15Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1941.5395346701005,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 98.89567905132267,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 96
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 168,
      "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": 72,
      "draws": 47,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:37Z",
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1775.3612754351213,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 70.45903844353168,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 109
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 22,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:30Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1750.965809215415,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 64.57723496573112,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "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": "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": 12,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:45Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1731.8618926517001,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 61.13700892804711,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:claude-opus-4-8:47e9dafb56058af5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 22,
      "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-opus-4-8",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T08:04:24Z",
      "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": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1729.7796436772644,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 57.70515067638105,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 26.264004201400486,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 208,
      "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": 104,
      "draws": 82,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:17Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1701.0026010053057,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.57987941105307,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 104,
      "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": 52,
      "draws": 58,
      "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": 14,
      "max_score": null,
      "measured_at": "2026-09-10T10:00:08Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1684.8593509221103,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 52.67280906849635,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 36,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-09-10T09:57:30Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1647.3925469912467,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.92580124934712,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 52
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 66,
      "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": 27,
      "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-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": 11,
      "max_score": null,
      "measured_at": "2026-08-04T08:44:46Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1655.3294738631357,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.027298685176675,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 42.0271267253503,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 47,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-09-10T09:57:20Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1591.2257260959202,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.81130147891559,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 61,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-09-10T09:57:09Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1589.3898232530091,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.48069279237866,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "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": 83,
      "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": "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": 46,
      "max_score": null,
      "measured_at": "2026-09-10T09:53:50Z",
      "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": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1576.638708912993,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.41194233918621,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "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/qwen3.8-2.4t-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": 22,
      "max_score": null,
      "measured_at": "2026-09-10T09:52:39Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1555.0517257485558,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.297101237978474,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "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": "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": 20,
      "max_score": null,
      "measured_at": "2026-09-10T09:52:37Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1553.8558854814169,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.081754776942507,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 60,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-09-10T09:50:54Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1517.647170216129,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.56130308677311,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 113,
      "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": 53,
      "draws": 82,
      "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": 19,
      "max_score": null,
      "measured_at": "2026-09-10T09:50:56Z",
      "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": 113,
      "rating_method": "sequential_elo",
      "raw_elo": 1515.1242452926706,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.390163615050678,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 3.079290579084697,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 52,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-09-10T09:49:06Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.2607155527892,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.87099389668296,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 69,
      "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": 28,
      "max_score": null,
      "measured_at": "2026-09-10T06:12:59Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.65479163134,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 18.420844285465474,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:xiaomi-mimo-v2-5:b10f89265c5b1dcb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "draws": 40,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 8,
      "max_score": null,
      "measured_at": "2026-07-31T01:21:08Z",
      "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": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.949735935574,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 14.876831236011256,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 26.264004201400486,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "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": 90,
      "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": "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": 35,
      "max_score": null,
      "measured_at": "2026-09-10T09:49:12Z",
      "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": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.2925767129848,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 13.442672880681176,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "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": 67,
      "draws": 105,
      "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": 26,
      "max_score": null,
      "measured_at": "2026-09-10T04:40:04Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.4605593091374,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.913154477319852,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:gpt-5:fa08b5a89f0aa0b3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 43,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T08:04:56Z",
      "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": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.764023922726,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.515897799774466,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 206,
      "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": 74,
      "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": "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": 24,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:30Z",
      "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": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.7760281162512,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.3621226468018,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:592235e55055263e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 46,
      "draws": 84,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T08:44:46Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.947102088648,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 11.68296478061394,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 28.430533588759353,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 61,
      "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": "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": 12,
      "max_score": null,
      "measured_at": "2026-09-10T09:46:00Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.6936587759922,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.858956125600434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "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": 54,
      "draws": 99,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:15Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.9640933137862,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.683228762592293,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 56,
      "draws": 114,
      "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": 4,
      "max_score": null,
      "measured_at": "2026-09-10T07:12:57Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.4186117447339,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.341010847452775,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 166,
      "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": 63,
      "draws": 147,
      "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": 10,
      "max_score": null,
      "measured_at": "2026-09-10T07:13:04Z",
      "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": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.1288826180637,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 10.237515749847217,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 96,
      "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": 6,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:39Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.6921355670459,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 9.963827021369582,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 216,
      "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": 72,
      "draws": 200,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:58Z",
      "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": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.8631926503854,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 9.050334687326071,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 106,
      "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": 53,
      "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": "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": 3,
      "max_score": null,
      "measured_at": "2026-09-10T09:45:40Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.5809790659166,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 8.569180028204126,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:tencent-hy3-preview:39292dc0f6c6c917",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 22,
      "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": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T05:07:08Z",
      "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": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.1751466918467,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 7.834028495391087,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 2,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 98,
      "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": 6,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:45Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.1135913809594,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 7.518607942495322,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 166,
      "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": 63,
      "draws": 155,
      "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": 10,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:45Z",
      "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": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.8422506070183,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 7.484704864315055,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 240,
      "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": 88,
      "draws": 203,
      "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": 31,
      "max_score": null,
      "measured_at": "2026-09-10T06:12:57Z",
      "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": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.6097196384471,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 4.775250900350241,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 104,
      "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": 52,
      "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": "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": 9,
      "max_score": null,
      "measured_at": "2026-09-10T09:49:05Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.6961605830274,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 2.2211281793648086,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "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": 66,
      "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-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": "2026-09-10T11:06:16Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 2094.223525062207,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 264,
      "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": 132,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:04Z",
      "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": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1992.7001425373535,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 89.4371849014492,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 138,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03: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": 66,
      "draws": 16,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-09-10T11:05:19Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1892.739852440075,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 79.03699890255805,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 212,
      "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": 86,
      "draws": 5,
      "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": 36,
      "max_score": null,
      "measured_at": "2026-09-10T11:01:05Z",
      "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": 211,
      "rating_method": "sequential_elo",
      "raw_elo": 1862.9174588920664,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 76.6845715154764,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 72,
      "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": 34,
      "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": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:17:00Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1793.0866148930616,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 65.43559754230012,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 38.449493652678655,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "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": 66,
      "draws": 47,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-09-10T11:00:18Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1699.1383870159802,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 58.89408767141809,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 138,
      "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": 66,
      "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": "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": 43,
      "max_score": null,
      "measured_at": "2026-09-10T10:58:44Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1691.0287691045999,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 58.05033727237247,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03: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": 66,
      "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": "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": 40,
      "max_score": null,
      "measured_at": "2026-09-10T11:00:26Z",
      "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": 131,
      "rating_method": "sequential_elo",
      "raw_elo": 1664.6913668946706,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.29646688144744,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 5,
      "attempted_matches": 769,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:stealth-ox-alpha:650c74dfce556ee1",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 5,
      "distinct_rated_opponents": 330,
      "draws": 148,
      "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": 173,
      "max_score": null,
      "measured_at": "2026-09-10T11:01:05Z",
      "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": 632,
      "rating_method": "sequential_elo",
      "raw_elo": 1656.300862782808,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.34658467999775,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.009000729485333,
      "unilateral_faults": 131,
      "wins": 311
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "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": 66,
      "draws": 39,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-09-10T11:00:45Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1617.6146281467568,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.41209692545726,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "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": 66,
      "draws": 22,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-09-10T10:57:55Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1598.6883574866376,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.442947626880404,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "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": 66,
      "draws": 46,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-09-10T11:01:01Z",
      "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": 131,
      "rating_method": "sequential_elo",
      "raw_elo": 1571.8773387262142,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.63980066610449,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:google-gemini-3-6-flash:1efb2291cbf800fd",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 89,
      "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-3.6-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": 73,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:39Z",
      "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": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1542.5270863810842,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 43.44619039396651,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 138,
      "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": 66,
      "draws": 69,
      "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": 36,
      "max_score": null,
      "measured_at": "2026-09-10T10:51:20Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.1575815875583,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.87343571896586,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "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": 95,
      "draws": 90,
      "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": 84,
      "max_score": null,
      "measured_at": "2026-09-10T07:45:26Z",
      "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": 233,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.9590436872616,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.97211414971662,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:google-gemini-3-5-flash:27c90777b8ed242d",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 45,
      "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": 46,
      "max_score": null,
      "measured_at": "2026-09-10T10:48:35Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.9956475562567,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.08785360578334,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 151,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:qwen-qwen3-8-max:83f392701e202fd4",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 74,
      "draws": 22,
      "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": 74,
      "max_score": null,
      "measured_at": "2026-09-10T05:10:55Z",
      "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": 151,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.677115528226,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.20691764507233,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 55,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:gpt-5-5:df705e696fe9cc4f",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 26,
      "draws": 16,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:17:00Z",
      "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": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1515.9921221734,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.83597213035345,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:deepseek-deepseek-v4-pro:91e0c8a35047bbc6",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 49,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-09-10T08:26:55Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.430332315426,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 36.03496399223896,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 198,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:x-ai-grok-4-6:5c921eacd53762a9",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 99,
      "draws": 50,
      "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": 73,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:19Z",
      "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": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.3750031545576,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.43919418965659,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 210,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:meta-muse-spark-1-2:8ed12b9970d2209b",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "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": "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": 89,
      "max_score": null,
      "measured_at": "2026-09-10T10:54:31Z",
      "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": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.8229907189177,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.42644833802889,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 302,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:thinkingmachines-inkling:8db7573c02acc990",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 122,
      "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": 107,
      "max_score": null,
      "measured_at": "2026-09-10T08:21:00Z",
      "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": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.964326697737,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 34.083009309825044,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 268,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:moonshotai-kimi-k3:6cfd7a6936cf4591",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 97,
      "draws": 124,
      "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": 86,
      "max_score": null,
      "measured_at": "2026-09-10T08:15:07Z",
      "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": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.238678577864,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.72808628713718,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 172,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:thinkingmachines-inkling-small:bbca5c562fb1ab46",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "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": "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": 51,
      "max_score": null,
      "measured_at": "2026-09-10T10:55:16Z",
      "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": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.6089243701294,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.68895206775385,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:gpt-5-6-luna:0e3f3e6646cbf8db",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 92,
      "draws": 115,
      "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": 70,
      "max_score": null,
      "measured_at": "2026-09-10T10:52:53Z",
      "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": 237,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.133702959996,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.06553227928354,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 43,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:gpt-5:fa08b5a89f0aa0b3",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 17,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T03:06:54Z",
      "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": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.0397619411053,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.59173778794821,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 32.49928516630233,
      "unilateral_faults": 1,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:bytedance-seed-seed-2-0-code:87a10b251e401fd3",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 57,
      "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": 34,
      "max_score": null,
      "measured_at": "2026-09-10T10:47:25Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.4878724405924,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.56709410597149,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:o3:908e4e2cf254357c",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 83,
      "draws": 89,
      "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": 90,
      "max_score": null,
      "measured_at": "2026-09-10T10:50:33Z",
      "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": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.5139023514475,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.45724153790146,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:x-ai-grok-4-5:b0a92c183e177d45",
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 86,
      "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": "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": 74,
      "max_score": null,
      "measured_at": "2026-09-10T10:53:15Z",
      "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": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.539339692124,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.138548110434098,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:deepseek-deepseek-v4-flash:bd0b950926bd00a0",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "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": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-09-10T03:39:11Z",
      "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": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.8880325254963,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.23086777854394,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 510,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:google-gemini-3-5-flash-lite:abb2b9fa09f58cba",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 182,
      "draws": 120,
      "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": 181,
      "max_score": null,
      "measured_at": "2026-09-10T10:57:37Z",
      "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": 510,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.4432366699407,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.338111214731462,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 209
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 162,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:gpt-5-6-terra:7c2a658c6918f6e6",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 71,
      "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": 54,
      "max_score": null,
      "measured_at": "2026-09-10T05:53:10Z",
      "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": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.4320852241547,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.37278067295601,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 245,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:gpt-5-4:6f2d7de576c6f541",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 87,
      "draws": 84,
      "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": 79,
      "max_score": null,
      "measured_at": "2026-09-10T05:21:04Z",
      "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": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1382.2840850584937,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.86648580703239,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:z-ai-glm-5-2:d977e6638f849d00",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 78,
      "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": 28,
      "max_score": null,
      "measured_at": "2026-09-10T10:50:10Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1389.496297577414,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.677941438624654,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:claude-opus-4-5:0dacb4d5b9cf9367",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 94,
      "draws": 74,
      "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": 84,
      "max_score": null,
      "measured_at": "2026-09-10T08:16:08Z",
      "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": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1377.7612868151043,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.438809841777037,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:meta-muse-glimmer-30b:b931921706d77dd0",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 66,
      "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": 39,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:21Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1381.5176225686357,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.84781475496612,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:openai-gpt-oss-120b:e79c900fda7b779f",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 63,
      "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": 34,
      "max_score": null,
      "measured_at": "2026-09-10T10:49:44Z",
      "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": 133,
      "rating_method": "sequential_elo",
      "raw_elo": 1380.206473148802,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.724889026864293,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "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": 66,
      "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": "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": 30,
      "max_score": null,
      "measured_at": "2026-09-10T11:00:35Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1328.441766750424,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.32563417683313,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 114,
      "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": 57,
      "draws": 10,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-09-10T10:08:45Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1907.4055627869584,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 98.28111373405677,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 99
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 228,
      "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": 114,
      "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-5-1",
        "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": 29,
      "max_score": null,
      "measured_at": "2026-09-10T10:10:08Z",
      "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": 1848.9541347501813,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 88.60770691415766,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 185
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 186,
      "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": 77,
      "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": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-09-10T10:06:17Z",
      "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": 186,
      "rating_method": "sequential_elo",
      "raw_elo": 1799.4467778247522,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 81.74661371399337,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 139
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "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-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": 23,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:46Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1746.4555040374125,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 71.64471752845151,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "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": 91,
      "draws": 75,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-09-10T09:54:08Z",
      "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": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1699.4440706751725,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 65.77337510145159,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 118
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 112,
      "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": 47,
      "draws": 19,
      "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": 14,
      "max_score": null,
      "measured_at": "2026-08-05T04:13:16Z",
      "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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1722.0204237619773,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 65.0016466552378,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 22.507220868368073,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 342,
      "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": 171,
      "draws": 112,
      "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": 64,
      "max_score": null,
      "measured_at": "2026-09-10T10:15:30Z",
      "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": 342,
      "rating_method": "sequential_elo",
      "raw_elo": 1682.6073396219508,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 61.078178953791536,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 166
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "draws": 16,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-09-10T09:56:41Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1670.008152813912,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 58.99307917629111,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "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": "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": 30,
      "max_score": null,
      "measured_at": "2026-09-10T09:56:35Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1651.3628695260552,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.90738193032783,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 127,
      "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": 61,
      "draws": 52,
      "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": 26,
      "max_score": null,
      "measured_at": "2026-09-10T09:57:17Z",
      "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": 127,
      "rating_method": "sequential_elo",
      "raw_elo": 1617.0984767902028,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.55866652707872,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.444173824159213,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:claude-opus-4-8:47e9dafb56058af5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 24,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:54:41Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1622.394595844658,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.94611757043748,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "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": "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": 33,
      "max_score": null,
      "measured_at": "2026-09-10T09:53:09Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1580.7983584016195,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.22932296614858,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "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": "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": 59,
      "max_score": null,
      "measured_at": "2026-09-10T09:54:15Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1570.0749915745469,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.45466162285314,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 36
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 478,
      "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": 167,
      "draws": 131,
      "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": 147,
      "max_score": null,
      "measured_at": "2026-09-10T09:55:43Z",
      "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": 475,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.0651238854534,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.02102497124446,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 184,
      "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": 77,
      "draws": 90,
      "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": 42,
      "max_score": null,
      "measured_at": "2026-09-10T09:50:35Z",
      "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": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1541.4689786625354,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.02653543609264,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 189,
      "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": 79,
      "draws": 90,
      "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": 36,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:57Z",
      "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": 186,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.1929099684971,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 38.841449244307675,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 1,
      "attempted_matches": 134,
      "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": 67,
      "draws": 70,
      "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": 38,
      "max_score": null,
      "measured_at": "2026-09-10T01:13:16Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.4972986814284,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.24296791137236,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 140,
      "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": 70,
      "draws": 64,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-09-10T04:42:31Z",
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.9994974820688,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 30.628175763052685,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": "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": 58,
      "max_score": null,
      "measured_at": "2026-09-10T04:01:53Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.9508346481748,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.515021005587823,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 133,
      "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": 62,
      "draws": 92,
      "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": 19,
      "max_score": null,
      "measured_at": "2026-09-10T06:15:45Z",
      "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": 133,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.0691796694814,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.17902200488099,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 140,
      "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": 70,
      "draws": 78,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-09-10T07:13:06Z",
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.6448776444101,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.60464432138626,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:google-gemini-3-1-flash-lite:acd1e78007489bf4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 47,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:05:18Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.0998106127977,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.98788364443893,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:gpt-5:fa08b5a89f0aa0b3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 48,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:05:23Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.340762765141,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.862265180138433,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 184,
      "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": 92,
      "draws": 99,
      "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": 53,
      "max_score": null,
      "measured_at": "2026-09-10T10:15:30Z",
      "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": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.7570669799688,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.841660594454027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:xiaomi-mimo-v2-5:b10f89265c5b1dcb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 42,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 7,
      "max_score": null,
      "measured_at": "2026-07-31T02:31:03Z",
      "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": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.8007459421844,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.5961118118581,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 222,
      "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": 83,
      "draws": 146,
      "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": 39,
      "max_score": null,
      "measured_at": "2026-09-10T04:04:05Z",
      "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": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.5675354682323,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.416847410892895,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "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": 62,
      "draws": 92,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-09-10T04:44:59Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.6739310726407,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.270432377976235,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "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": 64,
      "draws": 53,
      "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": 42,
      "max_score": null,
      "measured_at": "2026-09-10T03:14:32Z",
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.5379926925962,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.843971005685763,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 140,
      "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": 70,
      "draws": 106,
      "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": 14,
      "max_score": null,
      "measured_at": "2026-09-10T07:15:44Z",
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.2741887633456,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 21.24043269755691,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 299,
      "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": 103,
      "draws": 167,
      "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": 100,
      "max_score": null,
      "measured_at": "2026-09-10T05:30:54Z",
      "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": 299,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.3582535632365,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 20.028370513249424,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "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": 58,
      "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": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-09-10T05:30:59Z",
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.6673306827304,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 19.436408028603687,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:tencent-hy3-preview:39292dc0f6c6c917",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 40,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:11:51Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.4471348945187,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 19.361118709233534,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "draws": 72,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:51Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.6225816346569,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 18.38304555561166,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "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": "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": 17,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:46Z",
      "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": 113,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.61860583031,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 18.355372189033734,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 3.079290579084697,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "draws": 82,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:38Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.484902413154,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.367291620527613,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 184,
      "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": 71,
      "draws": 116,
      "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": 45,
      "max_score": null,
      "measured_at": "2026-09-10T09:48:02Z",
      "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": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.1545682656892,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.294684637089965,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:gpt-5-5:df705e696fe9cc4f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 35,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T23:00:29Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.2086777568848,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.140349376902293,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:592235e55055263e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "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": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:29:54Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.2779463608167,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 16.95013592673012,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 467,
      "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": 160,
      "draws": 318,
      "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": 98,
      "max_score": null,
      "measured_at": "2026-09-10T09:51:02Z",
      "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": 465,
      "rating_method": "sequential_elo",
      "raw_elo": 1397.6493104991137,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 15.758295958987606,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 242,
      "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": 83,
      "draws": 103,
      "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": 76,
      "max_score": null,
      "measured_at": "2026-09-10T09:49:38Z",
      "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": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1387.6702135204537,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 14.194010354631436,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": "2026-09-10T10:39:41Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 2151.5735715815727,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 120
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:31Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 2049.821981812471,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 92.02404202093135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 107
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 10,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:25Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 2039.1287831280288,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 91.18583886791443,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "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": 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-5.4",
        "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": 22,
      "max_score": null,
      "measured_at": "2026-09-10T10:38:59Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 2022.8237873577302,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 90.58932194330986,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 484,
      "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": 175,
      "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": 85,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:07Z",
      "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": 484,
      "rating_method": "sequential_elo",
      "raw_elo": 1930.7302324494935,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 83.5278688201069,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 399
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:06Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1928.1615545368238,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 82.4874985834472,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 98
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 98,
      "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": 44,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-08-03T14:57:20Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1884.381955867567,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 77.46597085447985,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 27.056388861645896,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:gpt-5-5:df705e696fe9cc4f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:40:01Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1871.4415622354468,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 77.00277079448404,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "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": 90,
      "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": 72,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:07Z",
      "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": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1784.876545788455,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 72.09489879437513,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 120,
      "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": 60,
      "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": 45,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:13Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1788.349704659587,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 71.52812741168269,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 46,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:23Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1738.35460515231,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 67.60918311081942,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 206,
      "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": 88,
      "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": 60,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:07Z",
      "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": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1696.766819796055,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 65.02038273879721,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 146
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 57,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:24Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1641.3522369713987,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 60.00550031591886,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:tencent-hy3-preview:39292dc0f6c6c917",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T08:44:47Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1639.2073900533328,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 58.73748205542807,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 65,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:10Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1617.4113539089935,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 58.12885664164453,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 60,
      "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": 55,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:35Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1612.1526564637534,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 57.716645393220304,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:gpt-5:fa08b5a89f0aa0b3",
      "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": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T22:34:38Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1623.0296620496733,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 57.46936546828877,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 31
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 386,
      "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": 193,
      "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": 221,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:34Z",
      "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": 386,
      "rating_method": "sequential_elo",
      "raw_elo": 1603.5972040555732,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 57.13595607705878,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.0126757293056905,
      "unilateral_faults": 0,
      "wins": 165
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "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": 67,
      "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": 80,
      "max_score": null,
      "measured_at": "2026-09-10T04:38:48Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1569.950754355836,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.56042710751232,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 274,
      "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": 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-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": 124,
      "max_score": null,
      "measured_at": "2026-09-10T05:24:11Z",
      "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": 274,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.897963944819,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.03153887048955,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 130,
      "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": 65,
      "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": 72,
      "max_score": null,
      "measured_at": "2026-09-10T03:37:24Z",
      "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": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.3761215959112,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.690628075980555,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 120,
      "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": 60,
      "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": 70,
      "max_score": null,
      "measured_at": "2026-09-09T23:37:21Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1533.0356527584136,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 51.51493494903386,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.7045454545454586,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 210,
      "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": 87,
      "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": 109,
      "max_score": null,
      "measured_at": "2026-09-10T02:54:14Z",
      "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": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.290997711097,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 51.4429639826475,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 144,
      "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": 72,
      "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": 91,
      "max_score": null,
      "measured_at": "2026-09-10T04:38:47Z",
      "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": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.2842748535527,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.68357221574452,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:claude-opus-4-8:47e9dafb56058af5",
      "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": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:57:20Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1526.3767034116547,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.59206002860415,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 46
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 1035,
      "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": 360,
      "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": 499,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:46Z",
      "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": 1035,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.3768543058302,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.93788221593318,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 536
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 170,
      "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": 85,
      "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": 89,
      "max_score": null,
      "measured_at": "2026-09-10T05:28:37Z",
      "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": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.4193979704903,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.72447731658255,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 61,
      "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": 50,
      "max_score": null,
      "measured_at": "2026-09-10T08:08:18Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.2863092900893,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.36302826110043,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "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": 67,
      "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": 82,
      "max_score": null,
      "measured_at": "2026-09-10T05:26:53Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.4448278723703,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.03370945933072,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 148,
      "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": 74,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:07Z",
      "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": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.9428710696504,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.96749514971631,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 162,
      "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": 81,
      "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": 77,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:31Z",
      "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": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.4990644868933,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.81033417432173,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 288,
      "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": 90,
      "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": 140,
      "max_score": null,
      "measured_at": "2026-09-10T05:23:34Z",
      "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": 288,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.1401355707098,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.82596170566252,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 154,
      "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": 71,
      "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": 71,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:26Z",
      "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": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.6810024880726,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.821376524556854,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 144,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:592235e55055263e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 70,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:09:03Z",
      "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": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.012787457223,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 47.23542996577578,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 14.919558612226904,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:stepfun-step-3-7-flash:4d7c266d9504ba14",
      "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": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T10:09:34Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.3115832325407,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.46448138749022,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 139,
      "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": 65,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-09-09T21:24:45Z",
      "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": 139,
      "rating_method": "sequential_elo",
      "raw_elo": 1412.0945828140425,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.23525046231568,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:google-gemini-3-1-flash-lite:acd1e78007489bf4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:53:07Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1197.5672854163643,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.238563997706606,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 508,
      "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": 162,
      "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": 372,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:00Z",
      "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": 508,
      "rating_method": "sequential_elo",
      "raw_elo": 1140.5555835818523,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 21.63668679667324,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 522,
      "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": 170,
      "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": 405,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:06Z",
      "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": 522,
      "rating_method": "sequential_elo",
      "raw_elo": 1078.209332432158,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 16.775466878832237,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 118,
      "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": 59,
      "draws": 6,
      "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": 1,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:07Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 2147.0653496170057,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 111
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 14,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-09-10T10:25:56Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 2026.885219432552,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 90.60154698973984,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 93
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 11,
      "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": 21,
      "max_score": null,
      "measured_at": "2026-09-10T10:08:55Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1966.5752403122613,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 85.88512253636422,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 508,
      "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": 185,
      "draws": 26,
      "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": 107,
      "max_score": null,
      "measured_at": "2026-09-10T10:15:27Z",
      "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": 508,
      "rating_method": "sequential_elo",
      "raw_elo": 1951.3393726264744,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 85.6020891745296,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 375
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 206,
      "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": 84,
      "draws": 24,
      "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": 25,
      "max_score": null,
      "measured_at": "2026-09-10T10:10:09Z",
      "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": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1949.7197444262995,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 85.26032097966694,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 212,
      "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": 86,
      "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-5.4",
        "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": 40,
      "max_score": null,
      "measured_at": "2026-09-10T09:59:54Z",
      "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": 212,
      "rating_method": "sequential_elo",
      "raw_elo": 1877.695734805393,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 79.65866479600288,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 118,
      "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": 59,
      "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": "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": 26,
      "max_score": null,
      "measured_at": "2026-09-10T10:10:15Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1886.2027783372537,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 79.59975068636147,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 14,
      "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": 25,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:13Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1885.758929737167,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 79.56504037106075,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 206,
      "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": 85,
      "draws": 34,
      "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": 38,
      "max_score": null,
      "measured_at": "2026-09-10T10:05:47Z",
      "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": 205,
      "rating_method": "sequential_elo",
      "raw_elo": 1871.2923877720345,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 79.12179151899733,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 118,
      "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": 59,
      "draws": 16,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:33Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1817.1444184138888,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 74.19917615120977,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 44,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:gpt-5-5:df705e696fe9cc4f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 22,
      "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-5.5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:42:32Z",
      "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": 44,
      "rating_method": "sequential_elo",
      "raw_elo": 1837.2193099629035,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 73.97350967200747,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 30.785599249992988,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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-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": 38,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:50Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1811.6841955171515,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 73.77217005426371,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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": "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": 40,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:49Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1806.1969162678647,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 73.34304806796328,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 6,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-09-10T10:02:00Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1802.9206210982431,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 73.08683178535341,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 18,
      "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": 37,
      "max_score": null,
      "measured_at": "2026-09-10T10:00:07Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1797.2725457387294,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 72.64513505242988,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:claude-opus-4-8:47e9dafb56058af5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 19,
      "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-4-8",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T10:32:38Z",
      "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": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1799.4148654160863,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 70.79490986212144,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 14,
      "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": 42,
      "max_score": null,
      "measured_at": "2026-09-10T09:58:52Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1771.5461514507922,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 70.6332524935784,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 17,
      "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": 38,
      "max_score": null,
      "measured_at": "2026-09-10T09:59:53Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1756.280219142349,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 69.43940999034174,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:gpt-5:fa08b5a89f0aa0b3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 26,
      "draws": 3,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T13:30:44Z",
      "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": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1723.3452380747874,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 65.51337979360243,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 408,
      "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": 194,
      "draws": 62,
      "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": 119,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:32Z",
      "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": 408,
      "rating_method": "sequential_elo",
      "raw_elo": 1675.6494431146332,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 63.32717677815119,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 1,
      "attempted_matches": 138,
      "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": 69,
      "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": "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": 69,
      "max_score": null,
      "measured_at": "2026-09-10T03:21:43Z",
      "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": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1618.5910337917292,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 58.886001713839136,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:xiaomi-mimo-v2-5:b10f89265c5b1dcb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "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": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 26,
      "max_score": null,
      "measured_at": "2026-07-31T20:22:54Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1597.443682966158,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.88030293196678,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 320,
      "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": 107,
      "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": 152,
      "max_score": null,
      "measured_at": "2026-09-10T10:25:37Z",
      "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": 320,
      "rating_method": "sequential_elo",
      "raw_elo": 1561.5618918252717,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.3334397747058,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 308,
      "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": 101,
      "draws": 28,
      "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": 132,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:43Z",
      "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": 308,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.7762840301411,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 53.59615975953049,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 164,
      "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": 82,
      "draws": 10,
      "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": 68,
      "max_score": null,
      "measured_at": "2026-09-10T10:09:30Z",
      "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": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1532.4239830449544,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 52.36547411825162,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 177,
      "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": 85,
      "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": "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": 103,
      "max_score": null,
      "measured_at": "2026-09-10T07:37:36Z",
      "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": 177,
      "rating_method": "sequential_elo",
      "raw_elo": 1513.006229205502,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.937559609413256,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 288,
      "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": 89,
      "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": "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": 114,
      "max_score": null,
      "measured_at": "2026-09-10T10:15:29Z",
      "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": 288,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.4476857106802,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.694607148650334,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 156,
      "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": 73,
      "draws": 4,
      "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": 51,
      "max_score": null,
      "measured_at": "2026-09-10T06:18:39Z",
      "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": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.2457744100418,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.240345149208736,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:stepfun-step-3-7-flash:4d7c266d9504ba14",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 2,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:01:30Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.2172455852156,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.69828843610223,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 32
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 1137,
      "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": 366,
      "draws": 30,
      "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": 541,
      "max_score": null,
      "measured_at": "2026-09-10T10:09:06Z",
      "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": 1137,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.9750860855493,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.97644177549341,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 566
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 560,
      "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": 186,
      "draws": 25,
      "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": 293,
      "max_score": null,
      "measured_at": "2026-09-10T10:05:14Z",
      "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": 560,
      "rating_method": "sequential_elo",
      "raw_elo": 1386.774966776137,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.536391992160105,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 242
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 65,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:592235e55055263e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "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": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T23:17:48Z",
      "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": 65,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.1077884272852,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 41.07194976252669,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 17.79574548966636,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "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": 68,
      "draws": 6,
      "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": 59,
      "max_score": null,
      "measured_at": "2026-09-10T01:42:25Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1376.3097819269658,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.919571760376535,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 56,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:tencent-hy3-preview:39292dc0f6c6c917",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:52:58Z",
      "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": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1311.979408855983,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.417976363713066,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 65,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:google-gemini-3-1-flash-lite:acd1e78007489bf4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:35:51Z",
      "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": 65,
      "rating_method": "sequential_elo",
      "raw_elo": 1290.844080299784,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.05797596367991,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 17.79574548966636,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 7,
      "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": 59,
      "max_score": null,
      "measured_at": "2026-09-10T10:00:19Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1250.09057059966,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.853834414688254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "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": 77,
      "draws": 11,
      "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": 129,
      "max_score": null,
      "measured_at": "2026-09-10T09:58:34Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1187.329180941812,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.64947969953627,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 118,
      "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": 59,
      "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": 77,
      "max_score": null,
      "measured_at": "2026-09-10T10:05:38Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1144.2341444565989,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 21.57553878118651,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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": 80,
      "max_score": null,
      "measured_at": "2026-09-10T10:06:24Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1123.5806586176955,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 19.960373147257805,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "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": "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": 82,
      "max_score": null,
      "measured_at": "2026-09-10T10:15:29Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1092.640375258977,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.540748548543018,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 59,
      "draws": 2,
      "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": 93,
      "max_score": null,
      "measured_at": "2026-09-10T10:09:01Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1015.9346068947455,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 11.54212333087466,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 10,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:12Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 2085.516679771956,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 98.77394998739801,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 114
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 2,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:40Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 2085.499777586485,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 98.77254193497626,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 122
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "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": 85,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:35Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 2038.1479062581575,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 95.50333681723484,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 248,
      "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": 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-5-1",
        "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": 18,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:28Z",
      "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": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 2014.2567973068285,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 92.8375786081501,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 230
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "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": 24,
      "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": 1,
      "max_score": null,
      "measured_at": "2026-08-05T04:12:54Z",
      "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": 52,
      "rating_method": "sequential_elo",
      "raw_elo": 1939.9466836858041,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 85.05036844756516,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 24.930281974344517,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:gpt-5-5:df705e696fe9cc4f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:35:52Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1897.9650985373178,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 82.05925729033785,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 210,
      "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": 86,
      "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": 48,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:12Z",
      "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": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1843.711746417953,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 79.3166000382083,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 208,
      "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": 86,
      "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": 72,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:19Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1796.0495447757285,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 75.33510562810226,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "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": 62,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:17Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1799.8280691620685,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 74.97439218948013,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 39,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:15Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1797.9218119745026,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 74.8155896456324,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 85
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 140,
      "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": 65,
      "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": 46,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:09Z",
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1781.9845675213576,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 73.66211615758745,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 94
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:25Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1771.7419329089944,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 72.63465025280209,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:claude-opus-4-8:47e9dafb56058af5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:23:19Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1736.7603940051758,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 68.43443121361176,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 70,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:21Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1688.6451933819492,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 65.71219838826845,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "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": 85,
      "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": 85,
      "max_score": null,
      "measured_at": "2026-09-10T10:25:59Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1657.1377622614993,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 63.76292923051514,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "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": 62,
      "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": 54,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:26Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1659.5943657506098,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 63.292091931054706,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 67,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:36Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1656.7525702876383,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 63.05535349326236,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:43Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1653.943529613308,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 62.82134372387497,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 64,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:40Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1651.1504455479346,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 62.58866323477045,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 65,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:37Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1633.9085154706795,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 61.15230806980508,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 394,
      "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": 197,
      "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": 191,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:35Z",
      "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": 394,
      "rating_method": "sequential_elo",
      "raw_elo": 1612.2752770256213,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 59.42904163978228,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.529728340267163,
      "unilateral_faults": 0,
      "wins": 203
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "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": 64,
      "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": 78,
      "max_score": null,
      "measured_at": "2026-09-10T04:00:11Z",
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1611.935450984356,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 59.36839361358854,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:gpt-5:fa08b5a89f0aa0b3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T15:11:05Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1602.6753490524998,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 57.519301106513744,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 356,
      "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": 126,
      "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": 153,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:22Z",
      "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": 356,
      "rating_method": "sequential_elo",
      "raw_elo": 1555.2590306763939,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 55.81717567058087,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 298,
      "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": 101,
      "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": 143,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:23Z",
      "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": 298,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.6745398626697,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 54.18880756070461,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 140,
      "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": 70,
      "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": 79,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:24Z",
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.4117810372288,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 52.78791504126206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 274,
      "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": 93,
      "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": 144,
      "max_score": null,
      "measured_at": "2026-09-10T06:10:34Z",
      "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": 274,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.210308630917,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 52.151765643097974,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 300,
      "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": 100,
      "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": 143,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:32Z",
      "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": 300,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.746440183285,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 50.61905487171679,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 138,
      "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": 69,
      "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": 73,
      "max_score": null,
      "measured_at": "2026-09-10T01:35:09Z",
      "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": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.6605915888285,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 49.789511908530514,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 533,
      "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": 176,
      "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": 246,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:44Z",
      "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": 533,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.2476393987372,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.1277645295087,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 154,
      "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": 77,
      "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": 74,
      "max_score": null,
      "measured_at": "2026-09-10T08:07:41Z",
      "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": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.4326426470998,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.33821644839612,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 140,
      "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": 70,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-09-10T05:27:41Z",
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.9404458311392,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 46.08417494737303,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 178,
      "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": 89,
      "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": 91,
      "max_score": null,
      "measured_at": "2026-09-10T05:24:32Z",
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.8985365440951,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.64654917987288,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:google-gemini-3-1-flash-lite:acd1e78007489bf4",
      "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": "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:09:18Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.5857937905953,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 45.56327909407335,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 26
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 1174,
      "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": 390,
      "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": 631,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:21Z",
      "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": 1174,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.8637837101146,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 44.43538755960546,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 543
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 69,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:stepfun-step-3-7-flash:4d7c266d9504ba14",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:50:20Z",
      "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": 69,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.4173564751177,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 42.61480276704312,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 16.01143046671968,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:tencent-hy3-preview:39292dc0f6c6c917",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:12:54Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1318.9452867243672,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 33.99435555624251,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 268,
      "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": 88,
      "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": 177,
      "max_score": null,
      "measured_at": "2026-09-10T10:37:18Z",
      "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": 268,
      "rating_method": "sequential_elo",
      "raw_elo": 1279.0698787444887,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.54088523137084,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 124,
      "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": 62,
      "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": 68,
      "max_score": null,
      "measured_at": "2026-09-10T10:27:44Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1278.4467772054588,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.54023439724443,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "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": 64,
      "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": 101,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:01Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1175.0341089574347,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.05886622894134,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 99,
      "max_score": null,
      "measured_at": "2026-09-10T10:39:02Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1050.380743783233,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 12.540979465146396,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 62,
      "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": 109,
      "max_score": null,
      "measured_at": "2026-09-10T10:40:22Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 940.4778015280162,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 3.385411727320254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 61,
      "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": 3,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:12Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 2166.2747750373137,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 119
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08: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": 61,
      "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": "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": 20,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:17Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 2004.6104572049926,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 85.08829766988379,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 101
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 272,
      "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": 100,
      "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": 33,
      "max_score": null,
      "measured_at": "2026-09-10T10:09:31Z",
      "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": 272,
      "rating_method": "sequential_elo",
      "raw_elo": 1948.7095603306732,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 81.02581011754175,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 235
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 61,
      "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": 28,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:06Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1912.6127034227568,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 76.60254683856613,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 94
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 206,
      "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": 83,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-09-10T10:05:15Z",
      "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": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1879.7469609720076,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 74.33339438299416,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 152
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 206,
      "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": 84,
      "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": 60,
      "max_score": null,
      "measured_at": "2026-09-10T10:03:40Z",
      "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": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1840.334484911061,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 70.6980398471637,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 146
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 61,
      "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": 28,
      "max_score": null,
      "measured_at": "2026-09-10T10:15:31Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1824.43663835412,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 68.46930350710791,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 94
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-5-5:df705e696fe9cc4f",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "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-5.5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:02:23Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1795.716933688497,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 64.88666662466245,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 61,
      "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": 38,
      "max_score": null,
      "measured_at": "2026-09-10T10:05:58Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1767.790823738796,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 63.24436867228078,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 126,
      "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": 55,
      "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": 30,
      "max_score": null,
      "measured_at": "2026-08-05T04:44:12Z",
      "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": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1769.8149510159715,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 62.145467936039324,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 18.755723064737715,
      "unilateral_faults": 0,
      "wins": 96
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:claude-opus-4-8:47e9dafb56058af5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:16:17Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1722.852641589118,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 58.04739613214064,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 51
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 368,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:stealth-ox-alpha:650c74dfce556ee1",
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 184,
      "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": "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": 149,
      "max_score": null,
      "measured_at": "2026-09-10T10:26:17Z",
      "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": 368,
      "rating_method": "sequential_elo",
      "raw_elo": 1691.5039555971996,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 56.216676213796916,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.2127743389130075,
      "unilateral_faults": 0,
      "wins": 170
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-5-4:6f2d7de576c6f541",
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 83,
      "draws": 27,
      "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": 85,
      "max_score": null,
      "measured_at": "2026-09-10T11:09:05Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1604.0284164228153,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 48.913780813210096,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 3,
      "attempted_matches": 802,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:o3:908e4e2cf254357c",
      "capped_draws": 393,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 286,
      "draws": 393,
      "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": 205,
      "max_score": null,
      "measured_at": "2026-09-10T11:10:18Z",
      "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": 802,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.9587134875176,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.423745439118036,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 128,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:google-gemini-3-8-flash:7ef3571107626567",
      "capped_draws": 41,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "draws": 41,
      "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": 55,
      "max_score": null,
      "measured_at": "2026-09-09T22:53:54Z",
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.9177376052087,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 39.35230726139709,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 542,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:google-gemini-3-6-flash:1efb2291cbf800fd",
      "capped_draws": 212,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 195,
      "draws": 212,
      "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": 150,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:05Z",
      "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": 542,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.5632904173685,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 38.850120833000595,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:google-gemini-3-5-flash:27c90777b8ed242d",
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "draws": 49,
      "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": 58,
      "max_score": null,
      "measured_at": "2026-09-09T22:54:43Z",
      "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": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.919514273735,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.75365188750678,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 142,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:claude-fable-5:f2454da3451cc4f4",
      "capped_draws": 59,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 71,
      "draws": 59,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-09-10T04:17:05Z",
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.147621438758,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.59961008402652,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:bytedance-seed-seed-2-0-code:87a10b251e401fd3",
      "capped_draws": 63,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "draws": 63,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-09-09T23:36:18Z",
      "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": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.6155341744773,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 37.414213664906036,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 152,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:x-ai-grok-4-6:5c921eacd53762a9",
      "capped_draws": 56,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 76,
      "draws": 56,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-09-10T03:31:28Z",
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.9229355470898,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.65216676371213,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:tencent-hy3-preview:39292dc0f6c6c917",
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "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": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:45:25Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.3689594436266,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 35.22230343851298,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 192,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-5-6-terra:7c2a658c6918f6e6",
      "capped_draws": 72,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 96,
      "draws": 72,
      "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": 85,
      "max_score": null,
      "measured_at": "2026-09-10T06:45:56Z",
      "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": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.7667844873795,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 32.920915263210404,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 170,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:qwen-qwen3-8-27b:a0a78367379103f7",
      "capped_draws": 60,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 85,
      "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": "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": 76,
      "max_score": null,
      "measured_at": "2026-09-10T05:35:56Z",
      "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": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.3847926961248,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 31.79762104206238,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 138,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:592235e55055263e",
      "capped_draws": 96,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 67,
      "draws": 96,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:29:22Z",
      "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": 1417.834665740927,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.865118502018596,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 16.237183532345085,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:xiaomi-mimo-v2-5:b10f89265c5b1dcb",
      "capped_draws": 53,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 53,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": 3,
      "max_score": null,
      "measured_at": "2026-07-31T02:38:23Z",
      "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": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.3599497088626,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 29.167744907216587,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-5:fa08b5a89f0aa0b3",
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 49,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T23:45:21Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1401.429423608086,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.776555776498935,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:google-gemini-3-1-flash-lite:acd1e78007489bf4",
      "capped_draws": 54,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 54,
      "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:15:42Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.3465620036277,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.658397977334666,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 149,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:thinkingmachines-inkling-small:bbca5c562fb1ab46",
      "capped_draws": 119,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "draws": 119,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-09-10T07:35:02Z",
      "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": 149,
      "rating_method": "sequential_elo",
      "raw_elo": 1388.9166480313115,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.611767026883896,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:stepfun-step-3-7-flash:4d7c266d9504ba14",
      "capped_draws": 46,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "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": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:38:29Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.3882975295737,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.327373127581367,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:qwen-qwen3-8-max:83f392701e202fd4",
      "capped_draws": 97,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 97,
      "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": 21,
      "max_score": null,
      "measured_at": "2026-09-10T07:29:55Z",
      "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": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1385.047314059996,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 28.137934382472274,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 146,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:deepseek-deepseek-v4-pro:91e0c8a35047bbc6",
      "capped_draws": 112,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "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": "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": 26,
      "max_score": null,
      "measured_at": "2026-09-10T11:09:46Z",
      "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": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1379.9427905062857,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.753445741329188,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 152,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:tencent-hy4-preview:aa03f826bc323244",
      "capped_draws": 132,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 76,
      "draws": 132,
      "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": 10,
      "max_score": null,
      "measured_at": "2026-09-10T05:33:12Z",
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1378.5701242686011,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 27.68709794444988,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:deepseek-deepseek-v4-flash:bd0b950926bd00a0",
      "capped_draws": 104,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": "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": 11,
      "max_score": null,
      "measured_at": "2026-09-10T09:47:57Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1370.3683072257907,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 26.61336401789957,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:openai-gpt-oss-120b:e79c900fda7b779f",
      "capped_draws": 112,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "draws": 112,
      "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": 14,
      "max_score": null,
      "measured_at": "2026-09-10T00:23:02Z",
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1356.0821010691934,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 25.347189462445694,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:z-ai-glm-5-2:d977e6638f849d00",
      "capped_draws": 107,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 107,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:11Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1349.1858370718082,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.65952105621167,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:meta-muse-glimmer-30b:b931921706d77dd0",
      "capped_draws": 110,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 110,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:12Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1342.896074063688,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.079361655784513,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 276,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:thinkingmachines-inkling:8db7573c02acc990",
      "capped_draws": 195,
      "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": "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": 78,
      "max_score": null,
      "measured_at": "2026-09-10T11:08:22Z",
      "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": 276,
      "rating_method": "sequential_elo",
      "raw_elo": 1330.6232524994457,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 24.03053007285857,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 268,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:google-gemini-3-5-flash-lite:abb2b9fa09f58cba",
      "capped_draws": 200,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 91,
      "draws": 200,
      "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": 55,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:31Z",
      "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": 268,
      "rating_method": "sequential_elo",
      "raw_elo": 1326.4900962723918,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.616570657339402,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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": 2,
      "attempted_matches": 320,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:claude-opus-4-5:0dacb4d5b9cf9367",
      "capped_draws": 194,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 194,
      "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": 99,
      "max_score": null,
      "measured_at": "2026-09-10T11:11:52Z",
      "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": 320,
      "rating_method": "sequential_elo",
      "raw_elo": 1321.2243425653037,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 23.32111670246394,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:z-ai-glm-5-3-flash:cea57e181d1e302f",
      "capped_draws": 110,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 110,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-09-10T11:06:10Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1328.7367936612352,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.773328404903395,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:inception-mercury-2-5-preview:e936b6bbd630c36b",
      "capped_draws": 95,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 95,
      "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": 26,
      "max_score": null,
      "measured_at": "2026-09-10T11:05:37Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1324.9158440579301,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 22.420889079597504,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:deepseek-deepseek-v4-pro-0813:980c9c0ee71edcf8",
      "capped_draws": 102,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 102,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-09-10T11:09:39Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1285.5605334671657,
      "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 18.79080741094235,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-5-6-luna:0e3f3e6646cbf8db",
      "capped_draws": 164,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 164,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-09-10T11:08:37Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1267.149087461531,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260910-43fc3ba818c2",
      "row_kind": "game",
      "score": 17.840478169825914,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260910_111653",
      "suite_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
    }
  ],
  "schema_version": 11,
  "snapshot_id": "20260910_111653",
  "suite_line_id": "gamebench2",
  "suite_version": "2-known8-r3"
}