{
  "benchmark_line": "gamebench2",
  "comparability_tuples": [
    {
      "evaluation_family": "codegen_public_benchmark",
      "rating_method": "sequential_elo",
      "reasoning_effort": "balanced",
      "results_cut_id": "20260823_205116",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": "20260823_205116",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": "20260823_205116",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": "20260823_205116",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": "20260823_205116",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_kind": "overall"
    }
  ],
  "generated_at": "2026-08-23T20:51:16Z",
  "public_release_id": "gb2-20260823-7d5648862dc8",
  "results_cut_id": "gb2-20260823-7d5648862dc8",
  "rows": [
    {
      "admitted_plugins": 8,
      "attempted_matches": 690,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-sol:e615ab726629f0c0",
      "capped_draws": 3,
      "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": 85.0520428491399,
      "contributing_entrants": null,
      "distinct_rated_opponents": 321,
      "draws": 31,
      "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": "2026-08-23T09:27:52Z",
      "losses": 71,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 59.931879001613865,
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 690,
      "rating_method": "sequential_elo",
      "raw_elo": 1842.64076591568,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 85.0520428491399,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 588
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 736,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-fable-5:9765333017ba86fe",
      "capped_draws": 1,
      "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": 1.91725,
        "mean": 1.58262125,
        "median": 1.5854,
        "min": 1.05322,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 12.66097
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 83.8181052528922,
      "contributing_entrants": null,
      "distinct_rated_opponents": 330,
      "draws": 98,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "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": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04"
      ],
      "infra_failures_excluded": 4,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:44:21Z",
      "losses": 116,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 68.72658602086715,
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 736,
      "rating_method": "sequential_elo",
      "raw_elo": 1855.1245626866132,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 83.8181052528922,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 522
    },
    {
      "admitted_plugins": 13,
      "attempted_matches": 922,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-5:a953aed661ace78d",
      "capped_draws": 2,
      "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": 81.94688975391686,
      "contributing_entrants": null,
      "distinct_rated_opponents": 394,
      "draws": 66,
      "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": 158,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 61.97751151718376,
      "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": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 922,
      "rating_method": "sequential_elo",
      "raw_elo": 1820.8074000032345,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 77.80156217109193,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 698
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1358,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-5:b56db7c91f30e821",
      "capped_draws": 19,
      "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": 76.02497290363772,
      "contributing_entrants": null,
      "distinct_rated_opponents": 679,
      "draws": 185,
      "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": 241,
      "max_score": 95.92764370282903,
      "measured_at": null,
      "min_score": 52.394609038466754,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": 0.875,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1358,
      "rating_method": "sequential_elo",
      "raw_elo": 1794.0569911901882,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 73.52893696868458,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 932
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 716,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4:00c166645bf94fd4",
      "capped_draws": 33,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 3.2933475,
        "mean": 2.642580625,
        "median": 2.681945,
        "min": 1.562975,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 21.140645
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 72.62310023439427,
      "contributing_entrants": null,
      "distinct_rated_opponents": 331,
      "draws": 140,
      "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-5.4",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": "2026-08-05T04:44:25Z",
      "losses": 120,
      "max_score": 98.8173965766658,
      "measured_at": null,
      "min_score": 37.49790231061323,
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 714,
      "rating_method": "sequential_elo",
      "raw_elo": 1787.5560433565538,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "XHigh (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-2",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 72.62310023439427,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 454
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 646,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4:483e8409583d40a0",
      "capped_draws": 15,
      "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": 72.94400582798815,
      "contributing_entrants": null,
      "distinct_rated_opponents": 292,
      "draws": 85,
      "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": "2026-08-22T08:04:25Z",
      "losses": 75,
      "max_score": 95.09441694960572,
      "measured_at": null,
      "min_score": 38.03814073039753,
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 643,
      "rating_method": "sequential_elo",
      "raw_elo": 1788.8684081424512,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 70.5491235566473,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 483
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 728,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-sol:683e7f269aa1d12e",
      "capped_draws": 13,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 12.915325,
        "mean": 10.059243749999998,
        "median": 10.0094025,
        "min": 8.401555,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 80.47395
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 68.04975666291118,
      "contributing_entrants": null,
      "distinct_rated_opponents": 330,
      "draws": 82,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 8,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:22:45Z",
      "losses": 205,
      "max_score": 99.04634600393882,
      "measured_at": null,
      "min_score": 27.509760361553635,
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 728,
      "rating_method": "sequential_elo",
      "raw_elo": 1689.860767419978,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "XHigh (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-2",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 68.04975666291118,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 14,
      "attempted_matches": 1526,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-5:2bf46853c4c2a3bc",
      "capped_draws": 122,
      "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": 70.35475020724844,
      "contributing_entrants": null,
      "distinct_rated_opponents": 740,
      "draws": 327,
      "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": "2026-08-21T15:53:02Z",
      "losses": 257,
      "max_score": 91.17466067700593,
      "measured_at": null,
      "min_score": 51.08859351407519,
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1525,
      "rating_method": "sequential_elo",
      "raw_elo": 1730.5012602540678,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 68.04487783235751,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 941
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 690,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-8:95b343605f7f7184",
      "capped_draws": 18,
      "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": 68.9455842674663,
      "contributing_entrants": null,
      "distinct_rated_opponents": 316,
      "draws": 89,
      "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": "2026-08-05T04:35:38Z",
      "losses": 185,
      "max_score": 81.45539006883097,
      "measured_at": null,
      "min_score": 51.00200589427959,
      "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": 690,
      "rating_method": "sequential_elo",
      "raw_elo": 1710.9049783822786,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 66.68197733259686,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 416
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 653,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-5:a77a9da79f1450e0",
      "capped_draws": 49,
      "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": 21.885474999999996
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 68.8969621273796,
      "contributing_entrants": null,
      "distinct_rated_opponents": 306,
      "draws": 126,
      "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": "2026-08-05T04:44:25Z",
      "losses": 147,
      "max_score": 92.32704029193545,
      "measured_at": null,
      "min_score": 27.370645611635616,
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 652,
      "rating_method": "sequential_elo",
      "raw_elo": 1757.2922541616808,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 66.63495154439632,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 379
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 628,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-fable-5:99e7b840e9269907",
      "capped_draws": 0,
      "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": 0.6981,
        "mean": 0.5046499999999999,
        "median": 0.511355,
        "min": 0.33027,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 4.0372
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 68.70642652869618,
      "contributing_entrants": null,
      "distinct_rated_opponents": 308,
      "draws": 69,
      "eligibility_flag": true,
      "entry_count": 7,
      "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": "unknown_legacy",
        "reasoning_policy_version": "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": 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": "2026-08-05T04:34:24Z",
      "losses": 148,
      "max_score": 76.8393903737067,
      "measured_at": null,
      "min_score": 55.133363671974216,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": 0.875,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 624,
      "rating_method": "sequential_elo",
      "raw_elo": 1728.0957648948586,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 66.45067157045091,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 407
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 696,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-sol:92a27bf667504f91",
      "capped_draws": 41,
      "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": 64.30777313996133,
      "contributing_entrants": null,
      "distinct_rated_opponents": 322,
      "draws": 102,
      "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": "2026-08-23T05:21:14Z",
      "losses": 150,
      "max_score": 88.72393191119036,
      "measured_at": null,
      "min_score": 34.46156161117417,
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 696,
      "rating_method": "sequential_elo",
      "raw_elo": 1669.0175172711272,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 64.30777313996133,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 444
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 1828,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-6-flash:b4583ef7c04d45cd",
      "capped_draws": 200,
      "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": 66.24088892568602,
      "contributing_entrants": null,
      "distinct_rated_opponents": 709,
      "draws": 301,
      "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": "2026-08-23T12:51:05Z",
      "losses": 484,
      "max_score": 90.98102138726986,
      "measured_at": null,
      "min_score": 47.781451793024814,
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1824,
      "rating_method": "sequential_elo",
      "raw_elo": 1700.4625265437035,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 61.644093105485865,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 1039
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1294,
      "canonical_public_row_identity": "publication-row.v1:mixed:x-ai-grok-4-5:5e133fd8ec34ed0c",
      "capped_draws": 46,
      "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": 0.5964052000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 60.36479324487097,
      "contributing_entrants": null,
      "distinct_rated_opponents": 490,
      "draws": 251,
      "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": "2026-08-23T09:27:52Z",
      "losses": 358,
      "max_score": 89.63424632680322,
      "measured_at": null,
      "min_score": 32.171720342982304,
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1294,
      "rating_method": "sequential_elo",
      "raw_elo": 1654.1768913068108,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 60.36479324487097,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 685
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 732,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-terra:75cc7f062ffaf091",
      "capped_draws": 46,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 11
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 12.137519999999999,
        "mean": 8.1660015625,
        "median": 8.18098,
        "min": 4.7142525,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 65.32801249999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 58.10431141243433,
      "contributing_entrants": null,
      "distinct_rated_opponents": 339,
      "draws": 157,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "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": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 8,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:35:30Z",
      "losses": 234,
      "max_score": 72.91627837470821,
      "measured_at": null,
      "min_score": 41.410294640288974,
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 732,
      "rating_method": "sequential_elo",
      "raw_elo": 1632.4184387979212,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 58.10431141243433,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 341
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 722,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-sol:db6839ea2087dc79",
      "capped_draws": 8,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.6689649999999999,
        "mean": 0.46799875,
        "median": 0.4352825,
        "min": 0.36661499999999997,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 10
        },
        "run_count": 9,
        "token_priced_attempt_count": 10,
        "total": 4.1199200000000005
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 59.797351992953644,
      "contributing_entrants": null,
      "distinct_rated_opponents": 358,
      "draws": 156,
      "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": "unknown_legacy",
        "reasoning_policy_version": "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": 0.7777777777777778,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_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",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 8,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:03:35Z",
      "losses": 181,
      "max_score": 76.98450629273803,
      "measured_at": null,
      "min_score": 45.54023061897745,
      "model_code_failure_rate": 0.1111111111111111,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": 0.8888888888888888,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 722,
      "rating_method": "sequential_elo",
      "raw_elo": 1655.3969536616216,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 1,
      "repaired_rate": 0.1111111111111111,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 58.06224472493103,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 385
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 842,
      "canonical_public_row_identity": "publication-row.v1:mixed:x-ai-grok-4-5:a7aa1873ad17dbcc",
      "capped_draws": 10,
      "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": 55.33875461534285,
      "contributing_entrants": null,
      "distinct_rated_opponents": 417,
      "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-4.5",
        "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": 248,
      "max_score": 85.92138340901016,
      "measured_at": null,
      "min_score": 26.601192408895606,
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 840,
      "rating_method": "sequential_elo",
      "raw_elo": 1618.764347220545,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 55.33875461534285,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 396
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1935,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-6-flash:13a24e3021af753a",
      "capped_draws": 125,
      "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": 56.609375270608496,
      "contributing_entrants": null,
      "distinct_rated_opponents": 819,
      "draws": 479,
      "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": "2026-08-23T09:38:44Z",
      "losses": 457,
      "max_score": 89.86912515095916,
      "measured_at": null,
      "min_score": 16.214567763911244,
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1935,
      "rating_method": "sequential_elo",
      "raw_elo": 1653.0653338230331,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 54.750788157268985,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 999
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 702,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-sol:e7389fafab42de55",
      "capped_draws": 17,
      "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": 54.36711997740288,
      "contributing_entrants": null,
      "distinct_rated_opponents": 323,
      "draws": 161,
      "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": "2026-08-23T03:03:24Z",
      "losses": 173,
      "max_score": 78.9860147584493,
      "measured_at": null,
      "min_score": 26.738936634036737,
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 702,
      "rating_method": "sequential_elo",
      "raw_elo": 1609.4823162331725,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "None (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 54.36711997740288,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 368
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 748,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-5-flash:5712a3e29dc27925",
      "capped_draws": 68,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "evidence_basis": "Provider-reported",
        "max": 0.5145615,
        "mean": 0.34875300000000004,
        "median": 0.335163,
        "min": 0.254883,
        "recorded_attempt_count": 19,
        "run_count": 8,
        "total": 2.7900240000000007
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 53.68699728666813,
      "contributing_entrants": null,
      "distinct_rated_opponents": 370,
      "draws": 240,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": "2026-08-05T05:04:12Z",
      "losses": 193,
      "max_score": 86.87039539493097,
      "measured_at": null,
      "min_score": 25.159108940712393,
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 746,
      "rating_method": "sequential_elo",
      "raw_elo": 1602.169401184616,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 8,
      "repaired_rate": 1.0,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 53.68699728666813,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 313
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 736,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4:672219b99ff5a80c",
      "capped_draws": 59,
      "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": 2.2669949999999996
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 53.66067604864086,
      "contributing_entrants": null,
      "distinct_rated_opponents": 332,
      "draws": 213,
      "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": "2026-08-23T08:23:52Z",
      "losses": 172,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 25.561074219037017,
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 736,
      "rating_method": "sequential_elo",
      "raw_elo": 1622.400562635271,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 53.66067604864086,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 351
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 724,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-luna:f9f63ab67ac1da8b",
      "capped_draws": 9,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.9975713999999999,
        "mean": 0.6329139249999999,
        "median": 0.6142170999999998,
        "min": 0.3971226,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 10
        },
        "run_count": 9,
        "token_priced_attempt_count": 10,
        "total": 5.761308199999999
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 54.71005073457028,
      "contributing_entrants": null,
      "distinct_rated_opponents": 345,
      "draws": 163,
      "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": "unknown_legacy",
        "reasoning_policy_version": "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": 7,
      "first_pass_rate": 0.7777777777777778,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_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",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 8,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:29:50Z",
      "losses": 237,
      "max_score": 80.36696920553993,
      "measured_at": null,
      "min_score": 20.364907326166584,
      "model_code_failure_rate": 0.1111111111111111,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": 0.8888888888888888,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 724,
      "rating_method": "sequential_elo",
      "raw_elo": 1632.448313891178,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "XHigh (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-2",
      "repaired_admitted": 1,
      "repaired_rate": 0.1111111111111111,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 53.12255892264815,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 324
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 688,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-sonnet-5:ec6362fd3d2a0220",
      "capped_draws": 15,
      "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": 2.80795
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 52.37905852733127,
      "contributing_entrants": null,
      "distinct_rated_opponents": 321,
      "draws": 163,
      "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": "2026-08-23T08:13:25Z",
      "losses": 199,
      "max_score": 80.99321920419641,
      "measured_at": null,
      "min_score": 18.196918446623908,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 688,
      "rating_method": "sequential_elo",
      "raw_elo": 1583.3089839226702,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 52.37905852733127,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 326
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1396,
      "canonical_public_row_identity": "publication-row.v1:mixed:moonshotai-kimi-k3:f0bfe8c58b2cc988",
      "capped_draws": 142,
      "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": 0.6080262000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 52.163081702045574,
      "contributing_entrants": null,
      "distinct_rated_opponents": 551,
      "draws": 416,
      "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": "2026-08-23T04:48:24Z",
      "losses": 377,
      "max_score": 96.03018425662745,
      "measured_at": null,
      "min_score": 22.900288191407675,
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1396,
      "rating_method": "sequential_elo",
      "raw_elo": 1574.9829607075385,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 52.163081702045574,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 603
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 730,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4:c42a41ea59ccc1f7",
      "capped_draws": 80,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.15985749999999999,
        "mean": 0.09356500000000001,
        "median": 0.07461,
        "min": 0.06826499999999999,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 0.7485199999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 52.06193325005171,
      "contributing_entrants": null,
      "distinct_rated_opponents": 359,
      "draws": 269,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": "2026-08-05T05:41:54Z",
      "losses": 154,
      "max_score": 98.61036508816744,
      "measured_at": null,
      "min_score": 19.06652602077495,
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 724,
      "rating_method": "sequential_elo",
      "raw_elo": 1594.1498934486663,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "None (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 52.06193325005171,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 301
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 786,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-5:1a25631bf54a6363",
      "capped_draws": 122,
      "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": 3.5428550000000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 51.90534748551461,
      "contributing_entrants": null,
      "distinct_rated_opponents": 389,
      "draws": 261,
      "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": 224,
      "max_score": 69.14142074882011,
      "measured_at": null,
      "min_score": 37.041752080817375,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 786,
      "rating_method": "sequential_elo",
      "raw_elo": 1580.2794666999134,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 51.90534748551461,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 301
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 686,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-luna:e05ef4cc93414f96",
      "capped_draws": 53,
      "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": 51.28058027835432,
      "contributing_entrants": null,
      "distinct_rated_opponents": 323,
      "draws": 200,
      "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": "2026-08-23T08:55:05Z",
      "losses": 177,
      "max_score": 82.02633954021168,
      "measured_at": null,
      "min_score": 23.445214369711753,
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 685,
      "rating_method": "sequential_elo",
      "raw_elo": 1595.3830770303243,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 51.28058027835432,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 308
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 601,
      "canonical_public_row_identity": "publication-row.v1:mixed:meta-muse-spark-1-2:0ef600658249027b",
      "capped_draws": 24,
      "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": 53.00511108061398,
      "contributing_entrants": null,
      "distinct_rated_opponents": 281,
      "draws": 135,
      "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": "2026-08-23T02:44:09Z",
      "losses": 157,
      "max_score": 80.14955515143204,
      "measured_at": null,
      "min_score": 28.53778014221482,
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 601,
      "rating_method": "sequential_elo",
      "raw_elo": 1609.5375276472273,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 51.26485841178251,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 309
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 758,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4:ef3925c3f5fdbb2d",
      "capped_draws": 60,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.712055,
        "mean": 0.49864374999999994,
        "median": 0.5065824999999999,
        "min": 0.29423750000000004,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 3.98915
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 49.70359062320072,
      "contributing_entrants": null,
      "distinct_rated_opponents": 373,
      "draws": 241,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": "2026-08-05T06:55:12Z",
      "losses": 204,
      "max_score": 84.95793522748247,
      "measured_at": null,
      "min_score": 19.148888518137927,
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 756,
      "rating_method": "sequential_elo",
      "raw_elo": 1575.7578907915588,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 49.70359062320072,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 311
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 782,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-5:959db58a0f4d59b9",
      "capped_draws": 98,
      "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": 46.955420779375146,
      "contributing_entrants": null,
      "distinct_rated_opponents": 390,
      "draws": 278,
      "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": 222,
      "max_score": 69.43814796420975,
      "measured_at": null,
      "min_score": 25.52082770903801,
      "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": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 782,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.552832132067,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 46.955420779375146,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 282
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 819,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4-mini:e296afd987da0af3",
      "capped_draws": 57,
      "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": 46.84330020788533,
      "contributing_entrants": null,
      "distinct_rated_opponents": 397,
      "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-5.4-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": 251,
      "max_score": 59.73623054906832,
      "measured_at": null,
      "min_score": 21.626339283900553,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 817,
      "rating_method": "sequential_elo",
      "raw_elo": 1534.319901237102,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 46.84330020788533,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 315
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1238,
      "canonical_public_row_identity": "publication-row.v1:mixed:moonshotai-kimi-k3:6a00f2f5a49a8584",
      "capped_draws": 153,
      "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": 2.3233295999999997
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 46.486279873467986,
      "contributing_entrants": null,
      "distinct_rated_opponents": 470,
      "draws": 391,
      "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": "2026-08-22T07:54:09Z",
      "losses": 406,
      "max_score": 67.00524526280067,
      "measured_at": null,
      "min_score": 19.758668893473487,
      "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": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1225,
      "rating_method": "sequential_elo",
      "raw_elo": 1521.23164675783,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 46.486279873467986,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 428
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 536,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-5-flash:2637a22cd82f12e9",
      "capped_draws": 64,
      "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": 0.6921525,
        "mean": 0.48907706250000005,
        "median": 0.483741,
        "min": 0.401826,
        "recorded_attempt_count": 18,
        "run_count": 8,
        "total": 3.9126165000000004
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 49.715987926047966,
      "contributing_entrants": null,
      "distinct_rated_opponents": 258,
      "draws": 153,
      "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": "google/gemini-3.5-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",
        "GB2-02"
      ],
      "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": "2026-08-05T05:04:52Z",
      "losses": 198,
      "max_score": 82.05588219794666,
      "measured_at": null,
      "min_score": 21.612048110556422,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": 0.75,
      "provider": "Google",
      "provider_key": "google",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 536,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.5978601956003,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 46.26593993904155,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 759,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5:16f7def69ce10ccd",
      "capped_draws": 77,
      "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": 45.95221951291531,
      "contributing_entrants": null,
      "distinct_rated_opponents": 360,
      "draws": 236,
      "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": 272,
      "max_score": 66.00620122264021,
      "measured_at": null,
      "min_score": 20.557432544949897,
      "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": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 758,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.2728230395549,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 45.95221951291531,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 250
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 622,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-8:c5e685ce6c400bea",
      "capped_draws": 23,
      "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": 46.4863977297371,
      "contributing_entrants": null,
      "distinct_rated_opponents": 309,
      "draws": 160,
      "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": 193,
      "max_score": 69.78217372191577,
      "measured_at": null,
      "min_score": 18.694108648166214,
      "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": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 622,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.6459007335875,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 44.96016608783939,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1275,
      "canonical_public_row_identity": "publication-row.v1:mixed:x-ai-grok-4-5:365663c1de2ba20d",
      "capped_draws": 134,
      "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": 0.5947035999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 44.881496329176954,
      "contributing_entrants": null,
      "distinct_rated_opponents": 499,
      "draws": 403,
      "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": "2026-08-23T13:45:16Z",
      "losses": 390,
      "max_score": 83.79628828599199,
      "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": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1275,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.6217428347634,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 44.881496329176954,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 482
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 786,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-luna:89e8232b6c428839",
      "capped_draws": 111,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.0093148,
        "mean": 0.007231125,
        "median": 0.0070676,
        "min": 0.0051605999999999996,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 9,
        "token_priced_attempt_count": 9,
        "total": 0.0630096
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 46.22178060626738,
      "contributing_entrants": null,
      "distinct_rated_opponents": 383,
      "draws": 303,
      "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": "unknown_legacy",
        "reasoning_policy_version": "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": 8,
      "first_pass_rate": 0.8888888888888888,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 8,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:17:39Z",
      "losses": 232,
      "max_score": 66.55694526663,
      "measured_at": null,
      "min_score": 19.534394534685426,
      "model_code_failure_rate": 0.1111111111111111,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": 0.8888888888888888,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 786,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.8962536374843,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 44.88058831600791,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 251
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 766,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-8:8ccf8977401d94db",
      "capped_draws": 108,
      "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": 44.86814560751494,
      "contributing_entrants": null,
      "distinct_rated_opponents": 376,
      "draws": 299,
      "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": 204,
      "max_score": 75.46636108950283,
      "measured_at": null,
      "min_score": 16.344385607773184,
      "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": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 766,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.655158437621,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 44.86814560751494,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 263
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 738,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-sonnet-5:906c16e3480819c2",
      "capped_draws": 75,
      "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": 0.4567,
        "mean": 0.36814250000000004,
        "median": 0.355077,
        "min": 0.234622,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 2.94514
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 44.43468609895779,
      "contributing_entrants": null,
      "distinct_rated_opponents": 351,
      "draws": 212,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 16,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:35:38Z",
      "losses": 286,
      "max_score": 66.53539430743486,
      "measured_at": null,
      "min_score": 15.623941414360715,
      "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": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 738,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.1150883848943,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (historical request variant 3)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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-variant-3",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh (historical request variant 3)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-3",
        "reasoning_bucket_label": "XHigh (historical request variant 3)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-3"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-3",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 44.43468609895779,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 240
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 776,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-sonnet-5:3d227889fd8fad8f",
      "capped_draws": 146,
      "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": 0.07806,
        "mean": 0.06121625,
        "median": 0.061152,
        "min": 0.049788,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.48973
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 44.318842850132526,
      "contributing_entrants": null,
      "distinct_rated_opponents": 385,
      "draws": 323,
      "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": "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": 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": "2026-08-05T05:41:08Z",
      "losses": 213,
      "max_score": 57.007926489898445,
      "measured_at": null,
      "min_score": 23.76930952639686,
      "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": 40,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 776,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.826054219258,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking 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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Thinking disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 44.318842850132526,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 240
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 636,
      "canonical_public_row_identity": "publication-row.v1:mixed:o3:f70fd8105d3dfec2",
      "capped_draws": 80,
      "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": 47.41858747665342,
      "contributing_entrants": null,
      "distinct_rated_opponents": 313,
      "draws": 158,
      "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": 225,
      "max_score": 59.630586714276724,
      "measured_at": null,
      "min_score": 35.65160344774605,
      "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": 41,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 636,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.8636372392284,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 44.12796791753164,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 253
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 716,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-sol:7aebae84d73affb6",
      "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",
        "failed_cell_count": 1,
        "max": 0.147405,
        "mean": 0.12146437500000001,
        "median": 0.124865,
        "min": 0.09045,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 9,
        "token_priced_attempt_count": 9,
        "total": 1.069485
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 45.2414721537087,
      "contributing_entrants": null,
      "distinct_rated_opponents": 354,
      "draws": 194,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04"
      ],
      "first_pass_admitted": 8,
      "first_pass_rate": 0.8888888888888888,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 8,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:17:02Z",
      "losses": 241,
      "max_score": 61.405209741565095,
      "measured_at": null,
      "min_score": 26.199687374521076,
      "model_code_failure_rate": 0.1111111111111111,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": 0.8888888888888888,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 710,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.7222597647703,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "None (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 43.92872494110315,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 25,
      "attempted_matches": 337,
      "canonical_public_row_identity": "publication-row.v1:mixed:stealth-ox-alpha:fe3b437dca2c4367",
      "capped_draws": 10,
      "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": 43.59998821261214,
      "contributing_entrants": null,
      "distinct_rated_opponents": 167,
      "draws": 61,
      "eligibility_flag": true,
      "entry_count": 23,
      "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": "2026-08-23T15:12:59Z",
      "losses": 81,
      "max_score": 50.86244134919709,
      "measured_at": null,
      "min_score": 35.45001529607838,
      "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": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 333,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.939016492073,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 43.59998821261214,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 191
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 598,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-pro:d03a9ec0db9a8b52",
      "capped_draws": 84,
      "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": 0.10909930499999998,
        "mean": 0.082847753875,
        "median": 0.084146916,
        "min": 0.03951746,
        "recorded_attempt_count": 16,
        "run_count": 8,
        "total": 0.662782031
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 46.78401626089681,
      "contributing_entrants": null,
      "distinct_rated_opponents": 288,
      "draws": 140,
      "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": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "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": 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": "2026-08-05T05:11:41Z",
      "losses": 252,
      "max_score": 74.1333084252556,
      "measured_at": null,
      "min_score": 30.850811557145292,
      "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": 44,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 598,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.3616732040916,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 43.53743286070221,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 6,
      "attempted_matches": 638,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-7-plus:e4e482b5c34e690f",
      "capped_draws": 112,
      "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": 45.846013941307554,
      "contributing_entrants": null,
      "distinct_rated_opponents": 302,
      "draws": 198,
      "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": 218,
      "max_score": 70.50103787240695,
      "measured_at": null,
      "min_score": 23.250211486876427,
      "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": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 638,
      "rating_method": "sequential_elo",
      "raw_elo": 1534.6652906120871,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 42.664523344243406,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 8,
      "attempted_matches": 724,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4:cea8a68bd875deb9",
      "capped_draws": 64,
      "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": 0.7687025
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.56820924627434,
      "contributing_entrants": null,
      "distinct_rated_opponents": 322,
      "draws": 218,
      "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": "2026-08-22T07:54:09Z",
      "losses": 240,
      "max_score": 73.87313912064397,
      "measured_at": null,
      "min_score": 17.424895818830112,
      "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": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 724,
      "rating_method": "sequential_elo",
      "raw_elo": 1512.9103970329572,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "None (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 42.56820924627434,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 266
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 794,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-terra:08cc40e91e1568bf",
      "capped_draws": 87,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 11
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.24673750000000003,
        "mean": 0.16744,
        "median": 0.15809499999999999,
        "min": 0.108735,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 1.3395199999999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.525135923402324,
      "contributing_entrants": null,
      "distinct_rated_opponents": 388,
      "draws": 290,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "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": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 8,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:18:32Z",
      "losses": 254,
      "max_score": 56.91665552510462,
      "measured_at": null,
      "min_score": 25.970772760443374,
      "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": 47,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 794,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.3319203879903,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 42.525135923402324,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 8,
      "attempted_matches": 580,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-2:f14efcbac580ffaa",
      "capped_draws": 88,
      "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": 42.11595469371872,
      "contributing_entrants": null,
      "distinct_rated_opponents": 290,
      "draws": 234,
      "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": 164,
      "max_score": 65.44552694683463,
      "measured_at": null,
      "min_score": 19.008405115879473,
      "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": 48,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 580,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.2147215764037,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 8,
      "repaired_rate": 1.0,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 42.11595469371872,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 182
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 1172,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-2:5ea14bc9644b6a2b",
      "capped_draws": 98,
      "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": 42.11163766096654,
      "contributing_entrants": null,
      "distinct_rated_opponents": 586,
      "draws": 386,
      "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": 408,
      "max_score": 57.774334362784295,
      "measured_at": null,
      "min_score": 16.009458011887702,
      "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": 49,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1172,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.5080965058964,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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",
          "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 42.11163766096654,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 19,
      "attempted_matches": 2921,
      "canonical_public_row_identity": "publication-row.v1:mixed:o3:1084c60ee563e860",
      "capped_draws": 224,
      "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": 0.07737849999999999,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 40
        },
        "recorded_attempt_count": 32,
        "run_count": 32,
        "token_priced_attempt_count": 8,
        "total": 2.927552
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": 47.39906310459903,
      "contributing_entrants": null,
      "distinct_rated_opponents": 1076,
      "draws": 289,
      "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": "2026-08-23T13:45:04Z",
      "losses": 1289,
      "max_score": 56.64546823346215,
      "measured_at": null,
      "min_score": 38.84780628544275,
      "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": 50,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2919,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.1668844285398,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 41.60740814708737,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1341
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 648,
      "canonical_public_row_identity": "publication-row.v1:mixed:moonshotai-kimi-k2-7-code:0eac35852db14de0",
      "capped_draws": 14,
      "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": 44.40080151631661,
      "contributing_entrants": null,
      "distinct_rated_opponents": 310,
      "draws": 184,
      "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": 223,
      "max_score": 64.14078623679886,
      "measured_at": null,
      "min_score": 23.349084470138546,
      "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": 51,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 648,
      "rating_method": "sequential_elo",
      "raw_elo": 1530.7330286175409,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 41.31960163911211,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 241
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 681,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-sonnet-5:a86621e2793b5dec",
      "capped_draws": 55,
      "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": 0.49337
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.870539430108586,
      "contributing_entrants": null,
      "distinct_rated_opponents": 324,
      "draws": 190,
      "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": "2026-08-23T12:40:55Z",
      "losses": 274,
      "max_score": 61.57727285827689,
      "measured_at": null,
      "min_score": 18.458780422070696,
      "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": 52,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 681,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.2081984517445,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking 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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Thinking disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 40.870539430108586,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 7,
      "attempted_matches": 740,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-7-max:fa240f0afd3eda59",
      "capped_draws": 106,
      "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": 0.7288237499999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.252226079601506,
      "contributing_entrants": null,
      "distinct_rated_opponents": 350,
      "draws": 267,
      "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": 247,
      "max_score": 72.79240290081826,
      "measured_at": null,
      "min_score": 15.965232157159793,
      "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": 53,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 740,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.240854679649,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 40.86500987157832,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 226
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 738,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-sonnet-5:e2e304f6cedf7237",
      "capped_draws": 95,
      "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": 0.132112,
        "mean": 0.0780535,
        "median": 0.06797,
        "min": 0.05673,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 0.624428
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.144128729302075,
      "contributing_entrants": null,
      "distinct_rated_opponents": 357,
      "draws": 244,
      "eligibility_flag": true,
      "entry_count": 7,
      "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": "unknown_legacy",
        "reasoning_policy_version": "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": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:04:02Z",
      "losses": 218,
      "max_score": 55.263664052390155,
      "measured_at": null,
      "min_score": 21.927203253446606,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": 0.875,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 54,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 738,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.280477998407,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 40.76046155076901,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 276
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 776,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-terra:0983009cb1ffeee4",
      "capped_draws": 113,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.1192425,
        "mean": 0.0683559375,
        "median": 0.06152125,
        "min": 0.0542775,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 10
        },
        "run_count": 9,
        "token_priced_attempt_count": 10,
        "total": 0.6063375000000001
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 41.9029728616441,
      "contributing_entrants": null,
      "distinct_rated_opponents": 384,
      "draws": 309,
      "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-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "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": 7,
      "first_pass_rate": 0.7777777777777778,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_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",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 8,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:05:30Z",
      "losses": 252,
      "max_score": 53.15064951506388,
      "measured_at": null,
      "min_score": 28.399082893812732,
      "model_code_failure_rate": 0.1111111111111111,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": 0.8888888888888888,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 55,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 774,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.7672841080805,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 1,
      "repaired_rate": 0.1111111111111111,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 40.68709706880698,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 213
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 654,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5:3bb27dbc092c7ff2",
      "capped_draws": 74,
      "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": 1.4205012499999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.04137766611068,
      "contributing_entrants": null,
      "distinct_rated_opponents": 319,
      "draws": 177,
      "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": 255,
      "max_score": 59.51888474627783,
      "measured_at": null,
      "min_score": 22.173830070391556,
      "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": 56,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 654,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.6960310752406,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 40.661083988892834,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 8,
      "attempted_matches": 681,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-sonnet-5:73f1b29a5c45562d",
      "capped_draws": 79,
      "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": 0.5249900000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.690544334888344,
      "contributing_entrants": null,
      "distinct_rated_opponents": 323,
      "draws": 206,
      "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": "2026-08-23T07:22:40Z",
      "losses": 266,
      "max_score": 50.09934354410103,
      "measured_at": null,
      "min_score": 28.504507698976763,
      "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": 57,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 681,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.6389315377035,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 39.690544334888344,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 658,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-7-max:a92ef5f3c3f212e3",
      "capped_draws": 109,
      "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": 40.86417247608275,
      "contributing_entrants": null,
      "distinct_rated_opponents": 321,
      "draws": 223,
      "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": 224,
      "max_score": 65.56652347725021,
      "measured_at": null,
      "min_score": 23.986859461426256,
      "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": 58,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 652,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.176154569393,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 39.52252855229327,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 7,
      "attempted_matches": 672,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-pro:a4cf9c7798e0d7dc",
      "capped_draws": 129,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.029078938,
        "mean": 0.015562441375000001,
        "median": 0.013116718500000001,
        "min": 0.005612805,
        "recorded_attempt_count": 12,
        "run_count": 8,
        "total": 0.124499531
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.828102714361634,
      "contributing_entrants": null,
      "distinct_rated_opponents": 330,
      "draws": 234,
      "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-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:27:08Z",
      "losses": 217,
      "max_score": 64.1672924244156,
      "measured_at": null,
      "min_score": 21.894015414373516,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": 0.875,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 59,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 672,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.3580308625667,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 39.4876430254095,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 221
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": 2319,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-5-flash-lite:55634764b9427e4e",
      "capped_draws": 332,
      "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": 0.27157109999999995
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 40.115968605994766,
      "contributing_entrants": null,
      "distinct_rated_opponents": 875,
      "draws": 773,
      "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": "2026-08-23T12:51:52Z",
      "losses": 858,
      "max_score": 69.37028762269674,
      "measured_at": null,
      "min_score": 9.276903456466506,
      "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": 60,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2311,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.9886081050195,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 39.473905934702984,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 680
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 693,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-luna:29e28a5adce9180a",
      "capped_draws": 71,
      "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": 0.050544450000000005
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.25231494426876,
      "contributing_entrants": null,
      "distinct_rated_opponents": 325,
      "draws": 219,
      "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": "2026-08-23T09:38:55Z",
      "losses": 270,
      "max_score": 59.663897931635695,
      "measured_at": null,
      "min_score": 24.254835093911925,
      "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": 61,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 692,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.6251795817846,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 39.25231494426876,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 203
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 750,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-4-1:731bd482a4919a05",
      "capped_draws": 86,
      "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": 39.175380343627474,
      "contributing_entrants": null,
      "distinct_rated_opponents": 371,
      "draws": 260,
      "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": 271,
      "max_score": 54.37710879884957,
      "measured_at": null,
      "min_score": 17.324048509285905,
      "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": 62,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 749,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.5198850774377,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 39.175380343627474,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 218
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 692,
      "canonical_public_row_identity": "publication-row.v1:mixed:meta-muse-spark-1-2:539f99e7c4c4b6ea",
      "capped_draws": 44,
      "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": 39.043450885870016,
      "contributing_entrants": null,
      "distinct_rated_opponents": 323,
      "draws": 166,
      "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": "2026-08-23T09:38:06Z",
      "losses": 299,
      "max_score": 57.58895419336781,
      "measured_at": null,
      "min_score": 16.50878695816217,
      "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": 63,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 692,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.0688339929347,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 39.043450885870016,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 227
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 1172,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4-nano:4caf0453cfb54e62",
      "capped_draws": 78,
      "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": 41.34035496936002,
      "contributing_entrants": null,
      "distinct_rated_opponents": 573,
      "draws": 225,
      "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": 495,
      "max_score": 61.40570645858217,
      "measured_at": null,
      "min_score": 13.75796311182292,
      "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": 64,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1170,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.445848406389,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 38.47153521149206,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 450
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 696,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-5:53d4c02c8a9496db",
      "capped_draws": 182,
      "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": 39.74621893216972,
      "contributing_entrants": null,
      "distinct_rated_opponents": 344,
      "draws": 354,
      "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": 187,
      "max_score": 51.810059046408426,
      "measured_at": null,
      "min_score": 22.09524395964808,
      "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": 65,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 696,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.6233072985822,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 38.44127942421412,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 155
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 834,
      "canonical_public_row_identity": "publication-row.v1:mixed:x-ai-grok-build-0-1:55f4f20890a40d69",
      "capped_draws": 116,
      "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": 0.48528460000000007
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 37.88184486713599,
      "contributing_entrants": null,
      "distinct_rated_opponents": 392,
      "draws": 318,
      "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": 294,
      "max_score": 63.41974151718129,
      "measured_at": null,
      "min_score": 21.669541208427077,
      "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": 66,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 834,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.802017654402,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 37.88184486713599,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 6,
      "attempted_matches": 560,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-flash:1ebaee0e9d08b232",
      "capped_draws": 95,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0221782524,
        "mean": 0.00999808046,
        "median": 0.009941171,
        "min": 0.00212373,
        "recorded_attempt_count": 14,
        "run_count": 8,
        "total": 0.07998464368000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.93877346153044,
      "contributing_entrants": null,
      "distinct_rated_opponents": 269,
      "draws": 155,
      "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": "deepseek/deepseek-v4-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": [
        "GB2-03",
        "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": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:43:54Z",
      "losses": 231,
      "max_score": 72.03816050961174,
      "measured_at": null,
      "min_score": 22.300174477766653,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": 0.75,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 67,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 560,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.0717561534093,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 37.167216649878206,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 6,
      "attempted_matches": 556,
      "canonical_public_row_identity": "publication-row.v1:mixed:tencent-hy3-preview:7ef07d2849ca4d92",
      "capped_draws": 108,
      "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": 39.18764503209153,
      "contributing_entrants": null,
      "distinct_rated_opponents": 272,
      "draws": 248,
      "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": 150,
      "max_score": 71.07282896064237,
      "measured_at": null,
      "min_score": 14.388654431203785,
      "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": 68,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 550,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.701921748651,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 36.46821288363263,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 152
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 1342,
      "canonical_public_row_identity": "publication-row.v1:mixed:poolside-laguna-s-2-1:533b6103a5973424",
      "capped_draws": 257,
      "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": 37.835105981413676,
      "contributing_entrants": null,
      "distinct_rated_opponents": 639,
      "draws": 461,
      "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": "2026-08-22T23:51:52Z",
      "losses": 460,
      "max_score": 54.815141934474596,
      "measured_at": null,
      "min_score": 18.971051988167996,
      "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": 69,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1333,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.2647513893937,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 36.40476713567153,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 412
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 2535,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-6-flash:b574aaabaed70f28",
      "capped_draws": 330,
      "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": 36.37905054510748,
      "contributing_entrants": null,
      "distinct_rated_opponents": 956,
      "draws": 909,
      "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": "2026-08-23T13:45:16Z",
      "losses": 937,
      "max_score": 52.7743268035604,
      "measured_at": null,
      "min_score": 17.072829141107093,
      "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": 70,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2531,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.094492438212,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 36.37905054510748,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 685
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 586,
      "canonical_public_row_identity": "publication-row.v1:mixed:minimax-minimax-m3:6639861dd7b73e51",
      "capped_draws": 32,
      "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": 38.2144104593529,
      "contributing_entrants": null,
      "distinct_rated_opponents": 291,
      "draws": 134,
      "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": 227,
      "max_score": 49.061655826617994,
      "measured_at": null,
      "min_score": 16.721194515766282,
      "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": 71,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 586,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.5517427700706,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 35.5625160611959,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 12,
      "attempted_matches": 1136,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4-nano:8753e840d1cee063",
      "capped_draws": 149,
      "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": 0.14744575000000004
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 37.47825265467621,
      "contributing_entrants": null,
      "distinct_rated_opponents": 560,
      "draws": 340,
      "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": 433,
      "max_score": 53.78745945851931,
      "measured_at": null,
      "min_score": 19.073029071771302,
      "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": 1130,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.6915537517432,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 34.877444031097845,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 357
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": 922,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5:235a446f3a9f9cd3",
      "capped_draws": 110,
      "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": 38.05314002836733,
      "contributing_entrants": null,
      "distinct_rated_opponents": 461,
      "draws": 289,
      "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": 329,
      "max_score": 49.49311656057918,
      "measured_at": null,
      "min_score": 19.548028827872443,
      "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": 73,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 922,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.1868873224719,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 34.650433704571576,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 304
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1856,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-5-flash-lite:5943a501fa6113ab",
      "capped_draws": 138,
      "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": 35.62010828184078,
      "contributing_entrants": null,
      "distinct_rated_opponents": 680,
      "draws": 456,
      "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": "2026-08-23T09:38:06Z",
      "losses": 844,
      "max_score": 53.05834174786712,
      "measured_at": null,
      "min_score": 24.21600641424555,
      "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": 74,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1855,
      "rating_method": "sequential_elo",
      "raw_elo": 1412.3948156552012,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 34.45063637172133,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 555
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 432,
      "canonical_public_row_identity": "publication-row.v1:mixed:openai-gpt-oss-120b:d658f92b65107751",
      "capped_draws": 67,
      "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": 0.01660212,
        "mean": 0.008820586750000001,
        "median": 0.007023681,
        "min": 0.00271606,
        "recorded_attempt_count": 19,
        "run_count": 8,
        "total": 0.070564694
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.58212869949016,
      "contributing_entrants": null,
      "distinct_rated_opponents": 210,
      "draws": 175,
      "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": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "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",
        "GB2-05"
      ],
      "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": "2026-08-05T05:11:31Z",
      "losses": 157,
      "max_score": 67.82204727657161,
      "measured_at": null,
      "min_score": 13.91305101107773,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 3,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": 0.625,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 75,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 432,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.0618356661885,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 34.30490253088758,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 578,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5:35035a0b78826dbc",
      "capped_draws": 88,
      "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": 36.51787511401212,
      "contributing_entrants": null,
      "distinct_rated_opponents": 285,
      "draws": 131,
      "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": 260,
      "max_score": 59.344201371796736,
      "measured_at": null,
      "min_score": 12.202269229827921,
      "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": 76,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 576,
      "rating_method": "sequential_elo",
      "raw_elo": 1397.5096469679254,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 33.983712025183316,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 185
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 524,
      "canonical_public_row_identity": "publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:be72f75fe8d3007b",
      "capped_draws": 98,
      "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": 36.17912444280867,
      "contributing_entrants": null,
      "distinct_rated_opponents": 262,
      "draws": 178,
      "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": 209,
      "max_score": 55.212486240190024,
      "measured_at": null,
      "min_score": 12.615617756799654,
      "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": 77,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 524,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.7480939277334,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 33.97597552234614,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 137
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 650,
      "canonical_public_row_identity": "publication-row.v1:mixed:tencent-hy3-preview:173ea133649c5bcd",
      "capped_draws": 44,
      "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": 36.126585006800155,
      "contributing_entrants": null,
      "distinct_rated_opponents": 315,
      "draws": 157,
      "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": 295,
      "max_score": 58.41330958645064,
      "measured_at": null,
      "min_score": 13.758406271721789,
      "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": 78,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 648,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.9272087886864,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 33.92663550598933,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 196
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 697,
      "canonical_public_row_identity": "publication-row.v1:mixed:openai-gpt-oss-120b:f9a4cf175428ff96",
      "capped_draws": 118,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 16
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.00444719,
        "mean": 0.0024656575,
        "median": 0.002155255,
        "min": 0.0011302579999999999,
        "recorded_attempt_count": 16,
        "run_count": 8,
        "total": 0.01972526
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 34.95147835537315,
      "contributing_entrants": null,
      "distinct_rated_opponents": 339,
      "draws": 314,
      "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": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-07"
      ],
      "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": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:12:06Z",
      "losses": 240,
      "max_score": 44.324242271963605,
      "measured_at": null,
      "min_score": 21.805843612607568,
      "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": 79,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 697,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.3086190207546,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 33.803958762497714,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 143
    },
    {
      "admitted_plugins": 26,
      "attempted_matches": 309,
      "canonical_public_row_identity": "publication-row.v1:mixed:stealth-ox-alpha:6719f8157bcde29f",
      "capped_draws": 21,
      "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": 34.60521774334546,
      "contributing_entrants": null,
      "distinct_rated_opponents": 154,
      "draws": 80,
      "eligibility_flag": true,
      "entry_count": 21,
      "evaluated_setting_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": "2026-08-23T14:12:11Z",
      "losses": 133,
      "max_score": 43.42288793742722,
      "measured_at": null,
      "min_score": 10.098703084006734,
      "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": 80,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 308,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.5558524662247,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 33.38909206008818,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 1222,
      "canonical_public_row_identity": "publication-row.v1:mixed:thinkingmachines-inkling:a1a9848a1d14b67e",
      "capped_draws": 107,
      "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": 35.47310379880186,
      "contributing_entrants": null,
      "distinct_rated_opponents": 595,
      "draws": 387,
      "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": "2026-08-05T05:41:54Z",
      "losses": 496,
      "max_score": 67.94308497290339,
      "measured_at": null,
      "min_score": 12.59254361838801,
      "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": 81,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1222,
      "rating_method": "sequential_elo",
      "raw_elo": 1393.3354036544079,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 33.01144276259816,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 339
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1446,
      "canonical_public_row_identity": "publication-row.v1:mixed:meituan-longcat-2-0:45102822fc5f9296",
      "capped_draws": 296,
      "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": 0.21404720400000002
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 33.67094708059916,
      "contributing_entrants": null,
      "distinct_rated_opponents": 701,
      "draws": 526,
      "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": "2026-08-05T05:41:26Z",
      "losses": 541,
      "max_score": 56.21511165223179,
      "measured_at": null,
      "min_score": 14.601235431191899,
      "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": 82,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1442,
      "rating_method": "sequential_elo",
      "raw_elo": 1376.6551199965613,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 32.565469621454156,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 375
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 768,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5:3449c1aec50b70b2",
      "capped_draws": 56,
      "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": 0.21411433159999999
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 34.40859764348753,
      "contributing_entrants": null,
      "distinct_rated_opponents": 360,
      "draws": 226,
      "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": 315,
      "max_score": 43.69988545387929,
      "measured_at": null,
      "min_score": 24.79337921651107,
      "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": 83,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 768,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.9713395799106,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 32.313265986893306,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 227
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 392,
      "canonical_public_row_identity": "publication-row.v1:mixed:cohere-north-mini-code:959513c67c4e5ee3",
      "capped_draws": 51,
      "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": 34.324135825057176,
      "contributing_entrants": null,
      "distinct_rated_opponents": 196,
      "draws": 190,
      "eligibility_flag": true,
      "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": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:19:01Z",
      "losses": 266,
      "max_score": 47.666905146048265,
      "measured_at": null,
      "min_score": 27.151591469186677,
      "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": 84,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 642,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.1591263613343,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 31.942207583278662,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 14,
      "attempted_matches": 1042,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-flash:dac448fbfe2a5737",
      "capped_draws": 184,
      "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": 0.05097333066
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 32.39306411364516,
      "contributing_entrants": null,
      "distinct_rated_opponents": 521,
      "draws": 369,
      "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": 431,
      "max_score": 47.63490899953319,
      "measured_at": null,
      "min_score": 16.923785423162606,
      "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": 85,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1042,
      "rating_method": "sequential_elo",
      "raw_elo": 1377.70761123024,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 31.329541839544742,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 8,
      "attempted_matches": 760,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5:32918e3c3e0fca83",
      "capped_draws": 61,
      "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": 33.78933230096341,
      "contributing_entrants": null,
      "distinct_rated_opponents": 358,
      "draws": 343,
      "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": 275,
      "max_score": 50.01827167679295,
      "measured_at": null,
      "min_score": 19.44142277101602,
      "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": 86,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 760,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.6514071160216,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 30.532108367789384,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 142
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 364,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5:024b37c390436d5a",
      "capped_draws": 112,
      "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": 0.19736108439999997
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 34.32762282883396,
      "contributing_entrants": null,
      "distinct_rated_opponents": 182,
      "draws": 231,
      "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": 85,
      "max_score": 55.77389183234963,
      "measured_at": null,
      "min_score": 17.065325253973946,
      "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": 87,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 364,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.8699538248118,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 30.522052436048757,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 28,
      "attempted_matches": 326,
      "canonical_public_row_identity": "publication-row.v1:mixed:stealth-ox-alpha:dfb3dd7361cfa1a2",
      "capped_draws": 15,
      "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": 30.666233135237924,
      "contributing_entrants": null,
      "distinct_rated_opponents": 161,
      "draws": 83,
      "eligibility_flag": true,
      "entry_count": 22,
      "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": "2026-08-23T15:12:59Z",
      "losses": 155,
      "max_score": 43.15000174191575,
      "measured_at": null,
      "min_score": 3.872072017351666,
      "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": 88,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 321,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.9877144950726,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 30.141830768739514,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 83
    },
    {
      "admitted_plugins": 9,
      "attempted_matches": 819,
      "canonical_public_row_identity": "publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:94c7956182cf2d89",
      "capped_draws": 152,
      "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": 34.73276605228333,
      "contributing_entrants": null,
      "distinct_rated_opponents": 402,
      "draws": 342,
      "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": 319,
      "max_score": 42.912176221849236,
      "measured_at": null,
      "min_score": 19.283288670132,
      "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": 89,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 819,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.18066394867,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 30.079457744979113,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 158
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 1854,
      "canonical_public_row_identity": "publication-row.v1:mixed:meituan-longcat-2-0:bed5035a5082adf8",
      "capped_draws": 116,
      "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": 31.99612108507919,
      "contributing_entrants": null,
      "distinct_rated_opponents": 699,
      "draws": 436,
      "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": "2026-08-23T10:07:05Z",
      "losses": 894,
      "max_score": 44.134251044046394,
      "measured_at": null,
      "min_score": 19.174525876824212,
      "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": 90,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1831,
      "rating_method": "sequential_elo",
      "raw_elo": 1373.2728197115905,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 29.775745754193835,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 23,
      "wins": 501
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 486,
      "canonical_public_row_identity": "publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:a3e60c7aa64704be",
      "capped_draws": 94,
      "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": 34.21970648915008,
      "contributing_entrants": null,
      "distinct_rated_opponents": 237,
      "draws": 186,
      "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": 177,
      "max_score": 60.46921496514469,
      "measured_at": null,
      "min_score": 10.757672736091521,
      "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": 91,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 486,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.5418005223532,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 29.54324213163337,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 5,
      "attempted_matches": 485,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-1-flash-lite:78a7cfd3a790e8a8",
      "capped_draws": 72,
      "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": 33.039846973976665,
      "contributing_entrants": null,
      "distinct_rated_opponents": 231,
      "draws": 136,
      "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": 254,
      "max_score": 44.84292897073299,
      "measured_at": null,
      "min_score": 19.73749709047673,
      "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": 92,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 485,
      "rating_method": "sequential_elo",
      "raw_elo": 1355.6660609099247,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 29.377039792329757,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 742,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4-mini:9285646640165917",
      "capped_draws": 117,
      "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": 29.208084954343278,
      "contributing_entrants": null,
      "distinct_rated_opponents": 364,
      "draws": 344,
      "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": 267,
      "max_score": 42.50170870197985,
      "measured_at": null,
      "min_score": 7.8623797518037435,
      "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": 93,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 738,
      "rating_method": "sequential_elo",
      "raw_elo": 1354.3385270828308,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 29.208084954343278,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 127
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 652,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-1-flash-lite:4c9cdde1729642af",
      "capped_draws": 84,
      "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": 30.637348965354164,
      "contributing_entrants": null,
      "distinct_rated_opponents": 320,
      "draws": 161,
      "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": 328,
      "max_score": 42.15860784753806,
      "measured_at": null,
      "min_score": 0.5504962648416883,
      "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": 94,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 650,
      "rating_method": "sequential_elo",
      "raw_elo": 1329.8076233730806,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 28.511265817165267,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 161
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 489,
      "canonical_public_row_identity": "publication-row.v1:mixed:stepfun-step-3-7-flash:0e0f63cf65826515",
      "capped_draws": 76,
      "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": 0.4860581
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 31.867344410388103,
      "contributing_entrants": null,
      "distinct_rated_opponents": 239,
      "draws": 78,
      "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": 265,
      "max_score": 42.18034696924738,
      "measured_at": null,
      "min_score": 12.522239497043625,
      "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": 95,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 489,
      "rating_method": "sequential_elo",
      "raw_elo": 1347.4262428175327,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 28.33452120880606,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 146
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 646,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-flash:865c6d4e9c2ee4b8",
      "capped_draws": 88,
      "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": 0.00408087,
        "mean": 0.0022664345375,
        "median": 0.0017928150000000001,
        "min": 0.0013289177,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.018131476299999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 28.29631741105212,
      "contributing_entrants": null,
      "distinct_rated_opponents": 320,
      "draws": 253,
      "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": "unknown_legacy",
        "reasoning_policy_version": "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"
      ],
      "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": "2026-08-05T05:23:15Z",
      "losses": 257,
      "max_score": 39.99912971379366,
      "measured_at": null,
      "min_score": 16.918306920549412,
      "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": 96,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 646,
      "rating_method": "sequential_elo",
      "raw_elo": 1360.900688836864,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 27.36729866382614,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 136
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": 1761,
      "canonical_public_row_identity": "publication-row.v1:mixed:poolside-laguna-s-2-1:07eac22bdea1b9b3",
      "capped_draws": 287,
      "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": 28.928846631529613,
      "contributing_entrants": null,
      "distinct_rated_opponents": 655,
      "draws": 722,
      "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": "2026-08-23T03:23:43Z",
      "losses": 724,
      "max_score": 39.01837754189059,
      "measured_at": null,
      "min_score": 20.800006608149722,
      "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": 97,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1759,
      "rating_method": "sequential_elo",
      "raw_elo": 1363.8492467367164,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 27.236248088672685,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 313
    },
    {
      "admitted_plugins": 9,
      "attempted_matches": 1352,
      "canonical_public_row_identity": "publication-row.v1:mixed:thinkingmachines-inkling:281eafa14f6ff011",
      "capped_draws": 162,
      "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": 31.033557017137518,
      "contributing_entrants": null,
      "distinct_rated_opponents": 493,
      "draws": 409,
      "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": "2026-08-23T09:56:43Z",
      "losses": 674,
      "max_score": 58.54870417164183,
      "measured_at": null,
      "min_score": 17.155695255029734,
      "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": 98,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1350,
      "rating_method": "sequential_elo",
      "raw_elo": 1341.3631138450419,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 26.875848746633917,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 267
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 742,
      "canonical_public_row_identity": "publication-row.v1:mixed:minimax-minimax-m3:6f48906184a5bdb8",
      "capped_draws": 97,
      "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": 27.729849405690125,
      "contributing_entrants": null,
      "distinct_rated_opponents": 351,
      "draws": 244,
      "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": 350,
      "max_score": 45.82355270808264,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": 0.875,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 99,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 742,
      "rating_method": "sequential_elo",
      "raw_elo": 1339.0013490733588,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 26.819428816982096,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 148
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 2125,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-5-flash-lite:0bab1c3ea19c7cb7",
      "capped_draws": 312,
      "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": 27.137514209400695,
      "contributing_entrants": null,
      "distinct_rated_opponents": 822,
      "draws": 713,
      "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": "2026-08-23T08:23:52Z",
      "losses": 1023,
      "max_score": 40.20117378359939,
      "measured_at": null,
      "min_score": 15.276461919221447,
      "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": 100,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2116,
      "rating_method": "sequential_elo",
      "raw_elo": 1319.1145617690274,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 26.246541045387577,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 380
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 492,
      "canonical_public_row_identity": "publication-row.v1:mixed:nex-agi-nex-n2-pro:a8c61d4550659ad0",
      "capped_draws": 18,
      "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": 28.182587082918843,
      "contributing_entrants": null,
      "distinct_rated_opponents": 237,
      "draws": 58,
      "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": 307,
      "max_score": 42.524739590732,
      "measured_at": null,
      "min_score": 11.297346143143717,
      "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": 101,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 492,
      "rating_method": "sequential_elo",
      "raw_elo": 1308.0891259112225,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 25.058257165591744,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 127
    },
    {
      "admitted_plugins": 10,
      "attempted_matches": 1324,
      "canonical_public_row_identity": "publication-row.v1:mixed:inclusionai-ling-3-0-flash:1ed2a890413ad375",
      "capped_draws": 375,
      "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": 27.734523333650188,
      "contributing_entrants": null,
      "distinct_rated_opponents": 506,
      "draws": 676,
      "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": 440,
      "max_score": 40.10360954415184,
      "measured_at": null,
      "min_score": 15.779988068257042,
      "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": 102,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1320,
      "rating_method": "sequential_elo",
      "raw_elo": 1336.4827726992785,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 24.659865895737095,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 204
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 553,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-7-plus:cdc5232f1e60910a",
      "capped_draws": 26,
      "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": 26.44462943801278,
      "contributing_entrants": null,
      "distinct_rated_opponents": 271,
      "draws": 180,
      "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": 255,
      "max_score": 45.76839619365652,
      "measured_at": null,
      "min_score": 4.247286587507169,
      "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": 103,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 551,
      "rating_method": "sequential_elo",
      "raw_elo": 1331.383402614363,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 23.89542014490823,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 116
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 727,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-luna:fd12531a88a47fab",
      "capped_draws": 120,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.007763,
        "mean": 0.0043935499999999995,
        "median": 0.0039395,
        "min": 0.0032303999999999996,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 0.035148399999999996
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 21.433403565791714,
      "contributing_entrants": null,
      "distinct_rated_opponents": 356,
      "draws": 309,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 8,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:41:40Z",
      "losses": 336,
      "max_score": 41.31733999385539,
      "measured_at": null,
      "min_score": 4.4033748279235585,
      "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": 104,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 721,
      "rating_method": "sequential_elo",
      "raw_elo": 1264.6961577346574,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "None (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 21.433403565791714,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 3,
      "wins": 76
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 693,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-luna:15a0f0a09f9eb8e5",
      "capped_draws": 30,
      "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": 20.068845020832462,
      "contributing_entrants": null,
      "distinct_rated_opponents": 326,
      "draws": 190,
      "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": "2026-08-23T12:40:55Z",
      "losses": 415,
      "max_score": 36.463037436242594,
      "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": 105,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 693,
      "rating_method": "sequential_elo",
      "raw_elo": 1272.9129330340154,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "None (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 20.068845020832462,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 370,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-1-flash-lite:f12274812b7e4c60",
      "capped_draws": 25,
      "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": 0.04706875
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 17.4455680741114,
      "contributing_entrants": null,
      "distinct_rated_opponents": 185,
      "draws": 85,
      "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": 212,
      "max_score": 39.0195992003968,
      "measured_at": null,
      "min_score": 0.0,
      "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": 106,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 370,
      "rating_method": "sequential_elo",
      "raw_elo": 1230.0089436034125,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 15.511547251312342,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1146,
      "canonical_public_row_identity": "publication-row.v1:mixed:openai-gpt-oss-120b:7785ef5b91a441ff",
      "capped_draws": 136,
      "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": 0.0032939400000000004,
        "mean": 0.0016413085000000001,
        "median": 0.0014119655,
        "min": 0.00045831,
        "recorded_attempt_count": 13,
        "run_count": 8,
        "total": 0.013130468000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 14.781157625670273,
      "contributing_entrants": null,
      "distinct_rated_opponents": 452,
      "draws": 244,
      "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": "openai/gpt-oss-120b",
        "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"
      ],
      "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": "2026-08-23T13:45:04Z",
      "losses": 738,
      "max_score": 22.92523467244584,
      "measured_at": null,
      "min_score": 0.0,
      "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": 107,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1146,
      "rating_method": "sequential_elo",
      "raw_elo": 1192.6216498361186,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 14.2958657645256,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 164
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 272,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-sonnet-5:72c37c305741dafa",
      "capped_draws": 8,
      "codegen_cost_usd": {
        "admitted_cell_count": 2,
        "cell_count": 1,
        "cost_basis_counts": {
          "local_list_price_estimate": 3
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.469661,
        "mean": 0.469661,
        "median": 0.469661,
        "min": 0.469661,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 2,
          "boardgame-list-prices-2026-08-08": 1
        },
        "run_count": 2,
        "token_priced_attempt_count": 3,
        "total": 0.939322
      },
      "codegen_evaluated_cells": 2,
      "conditional_success_score": 57.62901429743519,
      "contributing_entrants": null,
      "distinct_rated_opponents": 108,
      "draws": 104,
      "eligibility_flag": false,
      "entry_count": 2,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
        "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [
        "GB2-03"
      ],
      "infra_failures_excluded": 2,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-21T04:34:53Z",
      "losses": 69,
      "max_score": 57.62901429743519,
      "measured_at": null,
      "min_score": 57.62901429743519,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 272,
      "rating_method": "sequential_elo",
      "raw_elo": 1579.1406170036207,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "XHigh (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-2",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 57.62901429743519,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 99
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-2:7c1742483386cdf8",
      "capped_draws": 18,
      "codegen_cost_usd": {
        "admitted_cell_count": 2,
        "cell_count": 1,
        "cost_basis_counts": {
          "provider_reported": 7
        },
        "evidence_basis": "Provider-reported",
        "max": 0.09063263032999999,
        "mean": 0.09063263032999999,
        "median": 0.09063263032999999,
        "min": 0.09063263032999999,
        "recorded_attempt_count": 7,
        "run_count": 2,
        "total": 0.18126526065999998
      },
      "codegen_evaluated_cells": 2,
      "conditional_success_score": 51.704133366709385,
      "contributing_entrants": null,
      "distinct_rated_opponents": 86,
      "draws": 80,
      "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": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
        "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T14:35:20Z",
      "losses": 69,
      "max_score": 51.704133366709385,
      "measured_at": null,
      "min_score": 51.704133366709385,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1535.1007128451727,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 51.704133366709385,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 182,
      "canonical_public_row_identity": "publication-row.v1:mixed:meta-muse-spark-1-2:c4024993f2e98d89",
      "capped_draws": 13,
      "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": 51.295019038484355,
      "contributing_entrants": null,
      "distinct_rated_opponents": 86,
      "draws": 22,
      "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": [
        "below_generation_quality_threshold"
      ],
      "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": "2026-08-21T11:42:50Z",
      "losses": 71,
      "max_score": 53.82210709138648,
      "measured_at": null,
      "min_score": 48.767930985582225,
      "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": 182,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.459813823059,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 51.295019038484355,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1348,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-5:e2ff6744eb1bb7c6",
      "capped_draws": 72,
      "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": 1.4245200000000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 50.773332684552884,
      "contributing_entrants": null,
      "distinct_rated_opponents": 528,
      "draws": 347,
      "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-21T15:41:46Z",
      "losses": 421,
      "max_score": 82.15300774815739,
      "measured_at": null,
      "min_score": 22.143649514386354,
      "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": 1347,
      "rating_method": "sequential_elo",
      "raw_elo": 1567.1077432134841,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 50.773332684552884,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 579
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 756,
      "canonical_public_row_identity": "publication-row.v1:mixed:moonshotai-kimi-k3:ccf8a3c1c9260d55",
      "capped_draws": 21,
      "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": 52.396363285760984,
      "contributing_entrants": null,
      "distinct_rated_opponents": 289,
      "draws": 233,
      "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [
        "GB2-08"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T13:52:12Z",
      "losses": 193,
      "max_score": 80.31858860898552,
      "measured_at": null,
      "min_score": 23.676197661918458,
      "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": 756,
      "rating_method": "sequential_elo",
      "raw_elo": 1578.9701721531958,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 48.169166963777016,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 330
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": 0,
      "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": 4.09607
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 45.172931386644706,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 397,
      "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-31T20:23:03Z",
      "losses": 367,
      "max_score": 59.23297694417742,
      "measured_at": null,
      "min_score": 21.658118916144787,
      "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": 1126,
      "rating_method": "sequential_elo",
      "raw_elo": 1530.0303038655768,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 44.44993119484938,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 362
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1328,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-5:9f0371e603fb81bd",
      "capped_draws": 134,
      "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": 42.080323760465184,
      "contributing_entrants": null,
      "distinct_rated_opponents": 489,
      "draws": 373,
      "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T04:11:45Z",
      "losses": 485,
      "max_score": 63.991356251926845,
      "measured_at": null,
      "min_score": 13.32462959183295,
      "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": 1328,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.6743994437727,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 42.080323760465184,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 6,
      "attempted_matches": 538,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:4b9c2bdb10b14302",
      "capped_draws": 75,
      "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": 1.0777302952
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 44.414913787081844,
      "contributing_entrants": null,
      "distinct_rated_opponents": 258,
      "draws": 128,
      "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:11:01Z",
      "losses": 226,
      "max_score": 65.17750853680307,
      "measured_at": null,
      "min_score": 29.00219316035198,
      "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": 538,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.480717182855,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 41.332734586859196,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 184
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 129,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-max:7b21229bd01e0b5e",
      "capped_draws": 12,
      "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": 43.31650489789862,
      "contributing_entrants": null,
      "distinct_rated_opponents": 65,
      "draws": 36,
      "eligibility_flag": false,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [
        "GB2-02",
        "GB2-06",
        "GB2-08"
      ],
      "infra_failures_excluded": 3,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T12:51:05Z",
      "losses": 29,
      "max_score": 65.34857672458816,
      "measured_at": null,
      "min_score": 20.442652389870492,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 129,
      "rating_method": "sequential_elo",
      "raw_elo": 1554.971631815284,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 40.96622103853259,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 168,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-4-1-nano:68d5f0be3c90fb50",
      "capped_draws": 39,
      "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-2026-08-08": 1
        },
        "recorded_attempt_count": 1,
        "run_count": 1,
        "token_priced_attempt_count": 1,
        "total": 0.0023425
      },
      "codegen_evaluated_cells": 1,
      "conditional_success_score": 40.511310783890416,
      "contributing_entrants": null,
      "distinct_rated_opponents": 63,
      "draws": 39,
      "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-14T22:12:59Z",
      "losses": 69,
      "max_score": 40.511310783890416,
      "measured_at": null,
      "min_score": 40.511310783890416,
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.1019623450045,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 40.511310783890416,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 144,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-max:644816d2bc8a5f5c",
      "capped_draws": 11,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "evidence_basis": "Provider-reported",
        "max": 0.25803,
        "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": 39.301499454569424,
      "contributing_entrants": null,
      "distinct_rated_opponents": 75,
      "draws": 44,
      "eligibility_flag": false,
      "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T05:21:47Z",
      "losses": 41,
      "max_score": 53.968299220992186,
      "measured_at": null,
      "min_score": 11.78759779354171,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1526.3655621281673,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 39.301499454569424,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 558,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:36d8ebdcb946256c",
      "capped_draws": 38,
      "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": 39.50775450335153,
      "contributing_entrants": null,
      "distinct_rated_opponents": 276,
      "draws": 140,
      "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:17:07Z",
      "losses": 201,
      "max_score": 50.20183268472181,
      "measured_at": null,
      "min_score": 25.222210730949445,
      "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": 558,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.019223754377,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 38.01418194663798,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1,
      "attempted_matches": 178,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-sonnet-5:3db833e1d6821ccc",
      "capped_draws": 128,
      "codegen_cost_usd": {
        "admitted_cell_count": 1,
        "cell_count": 1,
        "cost_basis_counts": {
          "estimated": 1,
          "provider_dashboard_reconciled": 1
        },
        "evidence_basis": "Combined: Provider-reported + Recorded attempt",
        "max": 0.09014,
        "mean": 0.09014,
        "median": 0.09014,
        "min": 0.09014,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 1
        },
        "recorded_attempt_count": 2,
        "run_count": 1,
        "total": 0.09014
      },
      "codegen_evaluated_cells": 1,
      "conditional_success_score": 36.3482511329046,
      "contributing_entrants": null,
      "distinct_rated_opponents": 65,
      "draws": 128,
      "eligibility_flag": false,
      "entry_count": 1,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "unknown_legacy",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "unknown_legacy",
        "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T19:57:46Z",
      "losses": 36,
      "max_score": 36.3482511329046,
      "measured_at": null,
      "min_score": 36.3482511329046,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1387.0397820883597,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Unknown_legacy (historical request variant 3)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": null,
          "requested_effort": "historical-provider-setting-baseline-variant-3",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Unknown_legacy (historical request variant 3)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-3",
        "reasoning_bucket_label": "Unknown_legacy (historical request variant 3)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-3"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-3",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 36.3482511329046,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 444,
      "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": 41.52733113500447,
      "contributing_entrants": null,
      "distinct_rated_opponents": 207,
      "draws": 76,
      "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [
        "GB2-01"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:57:18Z",
      "losses": 197,
      "max_score": 55.00038838965367,
      "measured_at": null,
      "min_score": 35.53416954938754,
      "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": 442,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.231634839379,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 36.10559520111506,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 169
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 117,
      "canonical_public_row_identity": "publication-row.v1:mixed:thinkingmachines-inkling-small:c4a079d6b58a2c73",
      "capped_draws": 17,
      "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": 36.52576900215633,
      "contributing_entrants": null,
      "distinct_rated_opponents": 60,
      "draws": 44,
      "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": "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T03:04:42Z",
      "losses": 33,
      "max_score": 54.116030920939295,
      "measured_at": null,
      "min_score": 11.574430248545012,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 117,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.4824455565315,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 34.543939546177654,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 138,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-max:a791831295f0ee80",
      "capped_draws": 16,
      "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": 0.9576840000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 34.240469798169755,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 54,
      "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": "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T02:23:52Z",
      "losses": 45,
      "max_score": 61.919231042616644,
      "measured_at": null,
      "min_score": 7.491362721335916,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.16392752162,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 34.240469798169755,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 141,
      "canonical_public_row_identity": "publication-row.v1:mixed:thinkingmachines-inkling-small:f1451a0a6af20650",
      "capped_draws": 13,
      "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": 32.34497402709219,
      "contributing_entrants": null,
      "distinct_rated_opponents": 69,
      "draws": 50,
      "eligibility_flag": false,
      "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T08:13:39Z",
      "losses": 61,
      "max_score": 41.144919554096006,
      "measured_at": null,
      "min_score": 15.025055106927441,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 141,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.5612353522913,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 31.4064374924807,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 146,
      "canonical_public_row_identity": "publication-row.v1:mixed:thinkingmachines-inkling-small:6603774c29b8a046",
      "capped_draws": 15,
      "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": 32.114071254168294,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 54,
      "eligibility_flag": false,
      "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T08:02:59Z",
      "losses": 62,
      "max_score": 45.96450843356181,
      "measured_at": null,
      "min_score": 14.155329190210882,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.204868334078,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 31.182234699842784,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 414,
      "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": 36.456734403728596,
      "contributing_entrants": null,
      "distinct_rated_opponents": 202,
      "draws": 153,
      "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": 164,
      "max_score": 47.2576469157077,
      "measured_at": null,
      "min_score": 22.759457008176497,
      "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": 414,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.881190973985,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 30.656337271952143,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 610,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemma-4-31b-it:e2b2f6f0f78a1f3f",
      "capped_draws": 119,
      "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": 31.150644590364873,
      "contributing_entrants": null,
      "distinct_rated_opponents": 297,
      "draws": 190,
      "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [
        "GB2-02"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:48:11Z",
      "losses": 255,
      "max_score": 42.432414819587265,
      "measured_at": null,
      "min_score": 17.377509992236185,
      "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": 608,
      "rating_method": "sequential_elo",
      "raw_elo": 1335.852594591143,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 29.973008744719447,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 163
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 654,
      "canonical_public_row_identity": "publication-row.v1:mixed:stepfun-step-3-7-flash:b2de164dfb65fa47",
      "capped_draws": 104,
      "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": 0.19924717999999997
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 35.208732986034015,
      "contributing_entrants": null,
      "distinct_rated_opponents": 250,
      "draws": 115,
      "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": "2026-08-23T10:07:05Z",
      "losses": 330,
      "max_score": 50.91082045936282,
      "measured_at": null,
      "min_score": 22.117549019522556,
      "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": 650,
      "rating_method": "sequential_elo",
      "raw_elo": 1368.955564881608,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 29.606897353581214,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 7,
      "attempted_matches": 652,
      "canonical_public_row_identity": "publication-row.v1:mixed:nex-agi-nex-n2-pro:b04b6e7c11ec4633",
      "capped_draws": 103,
      "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": 2.586028
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 36.33161686261811,
      "contributing_entrants": null,
      "distinct_rated_opponents": 320,
      "draws": 295,
      "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": 197,
      "max_score": 60.50605278337446,
      "measured_at": null,
      "min_score": 16.55738720588751,
      "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": 652,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.242976410029,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 29.54807821865933,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 160
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 440,
      "canonical_public_row_identity": "publication-row.v1:mixed:mistralai-mistral-medium-3-5:6deb1b60bb205df7",
      "capped_draws": 101,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.06200699999999999,
        "mean": 0.042994687499999996,
        "median": 0.0423105,
        "min": 0.0223935,
        "recorded_attempt_count": 14,
        "run_count": 8,
        "total": 0.34395749999999997
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 34.34821004798081,
      "contributing_entrants": null,
      "distinct_rated_opponents": 201,
      "draws": 109,
      "eligibility_flag": false,
      "entry_count": 4,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "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",
        "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:02:41Z",
      "losses": 170,
      "max_score": 39.8933469399602,
      "measured_at": null,
      "min_score": 27.922700568650274,
      "model_code_failure_rate": 0.5,
      "model_code_failures": 4,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": 0.5,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 405,
      "rating_method": "sequential_elo",
      "raw_elo": 1365.418014434873,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 28.88328669972868,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 35,
      "wins": 126
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 829,
      "canonical_public_row_identity": "publication-row.v1:mixed:thinkingmachines-inkling:b27963da4b6944f2",
      "capped_draws": 134,
      "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": 30.876311405534096,
      "contributing_entrants": null,
      "distinct_rated_opponents": 332,
      "draws": 250,
      "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": "2026-08-22T12:49:16Z",
      "losses": 401,
      "max_score": 54.7905686677935,
      "measured_at": null,
      "min_score": 8.04764389452622,
      "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": 829,
      "rating_method": "sequential_elo",
      "raw_elo": 1337.094741645745,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 24.162019435171192,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 4,
      "attempted_matches": 663,
      "canonical_public_row_identity": "publication-row.v1:mixed:o3:29970c6bc7db3c37",
      "capped_draws": 159,
      "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-2026-08-08": 8
        },
        "recorded_attempt_count": 8,
        "run_count": 8,
        "token_priced_attempt_count": 13,
        "total": 0.8831579999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 26.89816985159589,
      "contributing_entrants": null,
      "distinct_rated_opponents": 250,
      "draws": 185,
      "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": "2026-08-23T12:51:52Z",
      "losses": 353,
      "max_score": 51.58180645988167,
      "measured_at": null,
      "min_score": 7.743053185185025,
      "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": 663,
      "rating_method": "sequential_elo",
      "raw_elo": 1287.4934568187057,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 22.61857460509252,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 6,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-row.v1:mixed:inclusionai-ling-3-0-flash:20c76d20ae9b2569",
      "capped_draws": 8,
      "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": 26.540316595936496,
      "contributing_entrants": null,
      "distinct_rated_opponents": 129,
      "draws": 263,
      "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"
      ],
      "infra_excluded_game_aliases": [
        "GB2-05"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T10:20:46Z",
      "losses": 509,
      "max_score": 41.40501950685979,
      "measured_at": null,
      "min_score": 12.133934164094017,
      "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": 1004,
      "rating_method": "sequential_elo",
      "raw_elo": 1378.707812217338,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 21.106736920958664,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 232
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 540,
      "canonical_public_row_identity": "publication-row.v1:mixed:cohere-north-mini-code:4a23759df70ab26b",
      "capped_draws": 194,
      "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": 26.84117147848124,
      "contributing_entrants": null,
      "distinct_rated_opponents": 248,
      "draws": 194,
      "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": 255,
      "max_score": 32.78188345286514,
      "measured_at": null,
      "min_score": 23.07648794314826,
      "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": 536,
      "rating_method": "sequential_elo",
      "raw_elo": 1292.9150741464903,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 20.068456528448355,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 87
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 366,
      "canonical_public_row_identity": "publication-row.v1:mixed:mistralai-mistral-medium-3-5:54288de170df8ebb",
      "capped_draws": 19,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.3927285,
        "mean": 0.1902770625,
        "median": 0.16804049999999998,
        "min": 0.08751,
        "recorded_attempt_count": 14,
        "run_count": 9,
        "total": 1.914945
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 21.11214296718544,
      "contributing_entrants": null,
      "distinct_rated_opponents": 179,
      "draws": 19,
      "eligibility_flag": false,
      "entry_count": 4,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "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",
        "GB2-08"
      ],
      "first_pass_admitted": 2,
      "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:22:40Z",
      "losses": 265,
      "max_score": 28.20923732650551,
      "measured_at": null,
      "min_score": 11.379446013072632,
      "model_code_failure_rate": 0.5555555555555556,
      "model_code_failures": 5,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": 0.4444444444444444,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 366,
      "rating_method": "sequential_elo",
      "raw_elo": 1212.7803751480983,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 17.23799254876425,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-max:83f392701e202fd4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": 10,
      "conditional_success_score": 0.0,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "eligibility_flag": false,
      "entry_count": 0,
      "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [
        "GB2-02",
        "GB2-06",
        "GB2-08"
      ],
      "infra_failures_excluded": 3,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": null,
      "max_score": 0.0,
      "measured_at": null,
      "min_score": 0.0,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "xhigh",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 0.0,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 26,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:mixed:stealth-ox-alpha:03024ebf053d776c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": 30,
      "conditional_success_score": 0.0,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "eligibility_flag": false,
      "entry_count": 0,
      "evaluated_setting_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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": null,
      "max_score": 0.0,
      "measured_at": null,
      "min_score": 0.0,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "high",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 0.0,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 28,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:mixed:stealth-ox-alpha:2a6c37bfc1ea9a10",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": 30,
      "conditional_success_score": 0.0,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "eligibility_flag": false,
      "entry_count": 0,
      "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": null,
      "max_score": 0.0,
      "measured_at": null,
      "min_score": 0.0,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "low",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 0.0,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 25,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:mixed:stealth-ox-alpha:650c74dfce556ee1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": 25,
      "conditional_success_score": 0.0,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "eligibility_flag": false,
      "entry_count": 0,
      "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [
        "GB2-02",
        "GB2-03"
      ],
      "infra_failures_excluded": 5,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": null,
      "max_score": 0.0,
      "measured_at": null,
      "min_score": 0.0,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "max",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 0.0,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:mixed:thinkingmachines-inkling-small:bbca5c562fb1ab46",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": 10,
      "conditional_success_score": 0.0,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "eligibility_flag": false,
      "entry_count": 0,
      "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": null,
      "max_score": 0.0,
      "measured_at": null,
      "min_score": 0.0,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "max",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 0.0,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01: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": 43,
      "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": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-19T23:51:30Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 2027.9678324469994,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 93
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-4:00c166645bf94fd4",
      "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": "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:35:41Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 2015.429236982834,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "XHigh (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 98.8173965766658,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 93
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-4:c42a41ea59ccc1f7",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:16:51Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 2013.7931496605154,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "None (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 98.61036508816744,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 88
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01: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": 42,
      "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": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-20T02:25:20Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1979.430767061083,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 95.09441694960572,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 91
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-5-flash:5712a3e29dc27925",
      "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": "google/gemini-3.5-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": 11,
      "max_score": null,
      "measured_at": "2026-07-31T03:28:21Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1899.4210224251667,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 86.87039539493097,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-sol:683e7f269aa1d12e",
      "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": "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:34:47Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1852.6117511208768,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "XHigh (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 82.47942500679652,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 170,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:x-ai-grok-4-5:5e133fd8ec34ed0c",
      "capped_draws": 32,
      "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": "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": 19,
      "max_score": null,
      "measured_at": "2026-08-23T08:55:05Z",
      "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": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1829.172240589223,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 80.96417402361442,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 119
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 42,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-08-23T08:55:05Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1836.192748563626,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 80.5273424342959,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-luna:f9f63ab67ac1da8b",
      "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": "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:47:20Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1832.8760948770332,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "XHigh (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 80.36696920553993,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01: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": 42,
      "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": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-20T01:48:05Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1832.923348449229,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 80.14955515143204,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-fable-5:9765333017ba86fe",
      "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": "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:38:01Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1824.3873130220802,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 79.58869492247467,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01: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": 42,
      "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": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-19T22:28:34Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1820.9424671159038,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "None (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 78.9860147584493,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:x-ai-grok-4-5:a7aa1873ad17dbcc",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "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": "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": 21,
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1777.1699941075071,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 74.81649706686221,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 2,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-4:cea8a68bd875deb9",
      "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": "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": 20,
      "max_score": null,
      "measured_at": "2026-08-19T23:52:11Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1767.2477663915254,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "None (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 73.69231856637961,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-5:a77a9da79f1450e0",
      "capped_draws": 30,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 30,
      "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": 16,
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1756.676617437372,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 72.70600935658693,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-fable-5:99e7b840e9269907",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-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": 26,
      "max_score": null,
      "measured_at": "2026-08-03T18:12:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1746.9451046530367,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 71.4108605082153,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 2,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-sol:e615ab726629f0c0",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": 21,
      "max_score": null,
      "measured_at": "2026-08-22T09:15:53Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1743.8724255296063,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 71.24245506978434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:tencent-hy3-preview:7ef07d2849ca4d92",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 19,
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1740.5175222083988,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 71.07282896064237,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 63
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 256,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-6-flash:13a24e3021af753a",
      "capped_draws": 97,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 111,
      "draws": 97,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 44,
      "max_score": null,
      "measured_at": "2026-08-22T09:26:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1726.9291590923472,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 70.09758000861065,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 115
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-5:2bf46853c4c2a3bc",
      "capped_draws": 105,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 117,
      "draws": 105,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-08-05T05:16:51Z",
      "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": 241,
      "rating_method": "sequential_elo",
      "raw_elo": 1717.6654625146953,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 69.11820487491038,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.6112092379023624,
      "unilateral_faults": 0,
      "wins": 113
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-4:ef3925c3f5fdbb2d",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 19,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T16:57:16Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1711.1296538562067,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 67.7403406860563,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 2,
      "wins": 49
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 210,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-5:b56db7c91f30e821",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 105,
      "draws": 19,
      "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": 64,
      "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": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1705.5104108029932,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 67.61473995183059,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.011966978180067,
      "unilateral_faults": 0,
      "wins": 127
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 145,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:moonshotai-kimi-k3:6a00f2f5a49a8584",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "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": "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": 48,
      "max_score": null,
      "measured_at": "2026-08-20T02:13:25Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1694.6446506662096,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 67.00524526280067,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-sonnet-5:906c16e3480819c2",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:47:09Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1695.23469264125,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (historical request variant 3)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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-variant-3",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh (historical request variant 3)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-3",
        "reasoning_bucket_label": "XHigh (historical request variant 3)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-3"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-3",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 66.53539430743486,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-luna:89e8232b6c428839",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T03:10:46Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1681.7158247375462,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 64.91454480895466,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 153,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-5:9f0371e603fb81bd",
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 26,
      "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": 36,
      "max_score": null,
      "measured_at": "2026-08-19T23:48:46Z",
      "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": 153,
      "rating_method": "sequential_elo",
      "raw_elo": 1662.883091394821,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 63.991356251926845,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-sol:db6839ea2087dc79",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "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-5.6-sol",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:23:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1661.0108027125154,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 63.03718007148168,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 62
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 128,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-5:a953aed661ace78d",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 57,
      "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-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": 47,
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1660.4981048082484,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 61.97751151718376,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.466769200052298,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 174,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:moonshotai-kimi-k3:ccf8a3c1c9260d55",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "draws": 17,
      "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": 59,
      "max_score": null,
      "measured_at": "2026-08-19T23:39:50Z",
      "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": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1633.9448139210695,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 61.26830836120785,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-sol:92a27bf667504f91",
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "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-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": 23,
      "max_score": null,
      "measured_at": "2026-08-22T19:57:46Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1644.1561281370252,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 61.164248353993486,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "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": 48,
      "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": 39,
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1628.750407707507,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 59.73623054906832,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 2,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-5:1a25631bf54a6363",
      "capped_draws": 65,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 65,
      "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": 14,
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1625.1613317167532,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 59.564351449683706,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:tencent-hy3-preview:173ea133649c5bcd",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 39,
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1614.8727554112447,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 58.41330958645064,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-8:95b343605f7f7184",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "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": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:35:46Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1609.684924746103,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 58.000169538136674,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 178,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-5:e2ff6744eb1bb7c6",
      "capped_draws": 51,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 72,
      "draws": 51,
      "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": 43,
      "max_score": null,
      "measured_at": "2026-08-19T23:49:22Z",
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1593.5115898273448,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 57.216109384642444,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-sonnet-5:ec6362fd3d2a0220",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-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": 28,
      "max_score": null,
      "measured_at": "2026-08-22T14:45:05Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1604.7460346224086,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 57.13530033302503,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-sonnet-5:3d227889fd8fad8f",
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 26,
      "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": "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": 35,
      "max_score": null,
      "measured_at": "2026-08-05T05:09:05Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1598.8545648282711,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking 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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Thinking disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 57.007926489898445,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 53
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 446,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:o3:1084c60ee563e860",
      "capped_draws": 32,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 169,
      "draws": 32,
      "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": 161,
      "max_score": null,
      "measured_at": "2026-08-22T09:26:27Z",
      "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": 446,
      "rating_method": "sequential_elo",
      "raw_elo": 1590.752419913073,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 56.64546823346215,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 253
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 56,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-08-05T04:26:53Z",
      "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": 113,
      "rating_method": "sequential_elo",
      "raw_elo": 1572.9878368669815,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.37710879884957,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.079290579084697,
      "unilateral_faults": 1,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-7-max:a92ef5f3c3f212e3",
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "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": "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": 30,
      "max_score": null,
      "measured_at": "2026-07-31T02:19:50Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1573.513576219901,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.19394021291321,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:meta-muse-spark-1-2:c4024993f2e98d89",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "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": "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": 37,
      "max_score": null,
      "measured_at": "2026-08-20T02:02:55Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1571.9644721957648,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 53.82210709138648,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 46
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 202,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-4-nano:8753e840d1cee063",
      "capped_draws": 54,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 96,
      "draws": 54,
      "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": 62,
      "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": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1569.9906928986984,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 53.78745945851931,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.625533144189548,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:be72f75fe8d3007b",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": 44,
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.6985011257657,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.991414623983445,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-8:c5e685ce6c400bea",
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 23,
      "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": 24,
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.0122470382578,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.971032291512834,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 91,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-luna:29e28a5adce9180a",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "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-5.6-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": 39,
      "max_score": null,
      "measured_at": "2026-08-20T02:03:00Z",
      "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": 91,
      "rating_method": "sequential_elo",
      "raw_elo": 1553.3629268180623,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 51.96516648339348,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.378603514268699,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-terra:0983009cb1ffeee4",
      "capped_draws": 30,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 30,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:05:30Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.0809635791695,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 51.380928870298845,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-sol:7aebae84d73affb6",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 12,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T02:07:28Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.020997495056,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "None (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.18934316422834,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 48
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 323,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-6-flash:b4583ef7c04d45cd",
      "capped_draws": 92,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 126,
      "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": "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": 117,
      "max_score": null,
      "measured_at": "2026-08-22T09:15:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 322,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.7173895347846,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 49.590003923577925,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 1,
      "wins": 113
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:a3e60c7aa64704be",
      "capped_draws": 20,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 20,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 36,
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1528.1057891742366,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 49.52252542484147,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-sonnet-5:e2e304f6cedf7237",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 10,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T09:49:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1525.1532485760156,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 49.265789786658594,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:minimax-minimax-m3:6639861dd7b73e51",
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": "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": 40,
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.7090711594628,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 49.061655826617994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-7-plus:e4e482b5c34e690f",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 18,
      "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": 42,
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1513.515357215152,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 48.12999209690405,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-5:53d4c02c8a9496db",
      "capped_draws": 92,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 92,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "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": 19,
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.7226018234821,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 47.92198712859516,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5:16f7def69ce10ccd",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 6,
      "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": 54,
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.6425409214996,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 47.822980600607565,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 50
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 194,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:xiaomi-mimo-v2-5:235a446f3a9f9cd3",
      "capped_draws": 36,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 97,
      "draws": 36,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 83,
      "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": 194,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.8698175351233,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.587241223773596,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.7753885573785855,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:xiaomi-mimo-v2-5:35035a0b78826dbc",
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "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": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:58:44Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.5178228047191,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.95098074818603,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 203,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:moonshotai-kimi-k3:f0bfe8c58b2cc988",
      "capped_draws": 139,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "draws": 139,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 32,
      "max_score": null,
      "measured_at": "2026-08-20T02:03:00Z",
      "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": 203,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.9678850754415,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.72944773324043,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 209,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:x-ai-grok-4-5:365663c1de2ba20d",
      "capped_draws": 134,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "draws": 134,
      "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": 36,
      "max_score": null,
      "measured_at": "2026-08-23T09:56:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 209,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.140841118312,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.4844504231055,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:x-ai-grok-build-0-1:55f4f20890a40d69",
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "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": "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": 43,
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.761287066289,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.273218336317015,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 42
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:poolside-laguna-s-2-1:533b6103a5973424",
      "capped_draws": 54,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 116,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 108,
      "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": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.0026155738424,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.7867759390862,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7092032923910905,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01: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": 21,
      "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": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-23T12:28:17Z",
      "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": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.8930518724999,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.48137058261478,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 89,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-sonnet-5:a86621e2793b5dec",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 16,
      "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": 45,
      "max_score": null,
      "measured_at": "2026-08-23T12:40:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 89,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.9176789585542,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking 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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Thinking disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.687018397883946,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.954627669472988,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-8:8ccf8977401d94db",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 17,
      "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": 39,
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.264528764638,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.63359523406752,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:o3:f70fd8105d3dfec2",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 46,
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.681575830985,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.55826547626181,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-terra:08cc40e91e1568bf",
      "capped_draws": 34,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 34,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:29:40Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.1014264525709,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.49963047361349,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 33
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 28,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:stealth-ox-alpha:6719f8157bcde29f",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 14,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 10,
      "max_score": null,
      "measured_at": "2026-08-23T12:28:17Z",
      "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": 28,
      "rating_method": "sequential_elo",
      "raw_elo": 1530.420159897876,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.42288793742722,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 85.34944487358055,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "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": 52,
      "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": 51,
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.399910028884,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 42.57288379544755,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-pro:a4cf9c7798e0d7dc",
      "capped_draws": 46,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:27:08Z",
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.1514954467345,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 42.49233284225822,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemma-4-31b-it:e2b2f6f0f78a1f3f",
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 40,
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.704251657997,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 42.432414819587265,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-pro:d03a9ec0db9a8b52",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 19,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:29:26Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.8732003554912,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 42.10203075533094,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-terra:75cc7f062ffaf091",
      "capped_draws": 31,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 31,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:35:46Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.6406737765797,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.410294640288974,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 19,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:thinkingmachines-inkling-small:f1451a0a6af20650",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "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": "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": 7,
      "max_score": null,
      "measured_at": "2026-08-22T09:27:15Z",
      "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": 19,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.0445342877708,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.144919554096006,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 68.05339887498948,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-8-max:644816d2bc8a5f5c",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 10,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 4,
      "max_score": null,
      "measured_at": "2026-08-22T16:31:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.3453591301432,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.01649081370751,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-1-flash-lite:4c9cdde1729642af",
      "capped_draws": 44,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "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": "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": 38,
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.0722052107417,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.98668493442913,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 89,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-sonnet-5:73f1b29a5c45562d",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 19,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-08-19T22:40:40Z",
      "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": 89,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.200355658939,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.88566173777684,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.954627669472988,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 168,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-4-1-nano:68d5f0be3c90fb50",
      "capped_draws": 39,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 39,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-08-14T22:12:59Z",
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.1019623450045,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.511310783890416,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 366,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-5-flash-lite:0bab1c3ea19c7cb7",
      "capped_draws": 73,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 142,
      "draws": 73,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 155,
      "max_score": null,
      "measured_at": "2026-08-22T19:58:37Z",
      "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": 366,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.2662451167348,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.20117378359939,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 138
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "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": 40,
      "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": 30,
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.7540280999642,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.0036272413998,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:mistralai-mistral-medium-3-5:6deb1b60bb205df7",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:02:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 101,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.8243444955588,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.8933469399602,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.757377148833722,
      "unilateral_faults": 35,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-5:959db58a0f4d59b9",
      "capped_draws": 77,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 77,
      "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": 26,
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.0475483689286,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.60642935936982,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 160,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:poolside-laguna-s-2-1:07eac22bdea1b9b3",
      "capped_draws": 28,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 28,
      "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": 74,
      "max_score": null,
      "measured_at": "2026-08-22T19:58:37Z",
      "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": 160,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.0856930075604,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.01837754189059,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:openai-gpt-oss-120b:f9a4cf175428ff96",
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 24,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:12:06Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.8019145344933,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.83660567477785,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:xiaomi-mimo-v2-5:32918e3c3e0fca83",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "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": "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": 56,
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.5069647830076,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.25295995113266,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:36d8ebdcb946256c",
      "capped_draws": 32,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "draws": 32,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 51,
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.395743836614,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.18442894600758,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:94c7956182cf2d89",
      "capped_draws": 20,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "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": "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": 52,
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.8528152679808,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.82037411124304,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 22
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 354,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-5-flash-lite:55634764b9427e4e",
      "capped_draws": 83,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 134,
      "draws": 83,
      "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": 160,
      "max_score": null,
      "measured_at": "2026-08-22T14:46:36Z",
      "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": 354,
      "rating_method": "sequential_elo",
      "raw_elo": 1388.3550597099304,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.47267278277283,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 178,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-sonnet-5:3db833e1d6821ccc",
      "capped_draws": 128,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 65,
      "draws": 128,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "unknown_legacy",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "unknown_legacy",
        "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": 36,
      "max_score": null,
      "measured_at": "2026-08-22T19:57:46Z",
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1387.0397820883597,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Unknown_legacy (historical request variant 3)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": null,
          "requested_effort": "historical-provider-setting-baseline-variant-3",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Unknown_legacy (historical request variant 3)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-3",
        "reasoning_bucket_label": "Unknown_legacy (historical request variant 3)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-3"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-3",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.3482511329046,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 314,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:inclusionai-ling-3-0-flash:1ed2a890413ad375",
      "capped_draws": 101,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 117,
      "draws": 101,
      "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": 120,
      "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": 314,
      "rating_method": "sequential_elo",
      "raw_elo": 1385.0409369204554,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.951635842394275,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 3,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:stealth-ox-alpha:dfb3dd7361cfa1a2",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 21,
      "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": "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": 27,
      "max_score": null,
      "measured_at": "2026-08-23T12:17:06Z",
      "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": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.826841528916,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.16566098009839,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:meta-muse-spark-1-2:539f99e7c4c4b6ea",
      "capped_draws": 39,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "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": "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": 44,
      "max_score": null,
      "measured_at": "2026-08-23T09:38:06Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1367.3882021779489,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 33.19164564959547,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:thinkingmachines-inkling:b27963da4b6944f2",
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "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": "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": 76,
      "max_score": null,
      "measured_at": "2026-08-15T02:21:14Z",
      "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": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.3433979275337,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 33.14168798272348,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:meituan-longcat-2-0:45102822fc5f9296",
      "capped_draws": 82,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 115,
      "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": "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": 95,
      "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": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1358.3905602002214,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.811959377744365,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.5464209114540584,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 152,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-flash:dac448fbfe2a5737",
      "capped_draws": 39,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 76,
      "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": "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": 82,
      "max_score": null,
      "measured_at": "2026-07-31T02:23:17Z",
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1360.8578517467413,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.116626000567756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-4-mini:9285646640165917",
      "capped_draws": 40,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 40,
      "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": 46,
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1351.113886438586,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.866704468526944,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-flash:1ebaee0e9d08b232",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "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": "deepseek/deepseek-v4-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": 51,
      "max_score": null,
      "measured_at": "2026-08-04T23:53:31Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1353.1558761739786,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.797564014719292,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 25
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 94,
      "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": 45,
      "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": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1338.8735053575797,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.090599422957155,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 140,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-5-flash-lite:5943a501fa6113ab",
      "capped_draws": 28,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 28,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 78,
      "max_score": null,
      "measured_at": "2026-08-23T09:38:06Z",
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1318.8398191425192,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.072445927965525,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 156,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:z-ai-glm-5-2:5ea14bc9644b6a2b",
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 78,
      "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": "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": 76,
      "max_score": null,
      "measured_at": "2026-07-31T03:20:17Z",
      "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": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1325.5609213423263,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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",
          "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 28.603518652489697,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-8-max:a791831295f0ee80",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 1,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-08-22T07:23:00Z",
      "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": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1364.0547383269693,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 27.24176104741712,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-7-plus:cdc5232f1e60910a",
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "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": "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": 55,
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1300.7914998768108,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.630246682212057,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:thinkingmachines-inkling-small:6603774c29b8a046",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "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": "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": 15,
      "max_score": null,
      "measured_at": "2026-08-22T09:26:27Z",
      "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": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1346.7122318417303,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.47208042284504,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "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": 48,
      "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": 68,
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1293.2880278495784,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 25.911126435305174,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:xiaomi-mimo-v2-5:3449c1aec50b70b2",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 60,
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1280.781906067578,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 24.79337921651107,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 47
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 348,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-6-flash:b574aaabaed70f28",
      "capped_draws": 82,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 131,
      "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-3.6-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": 186,
      "max_score": null,
      "measured_at": "2026-08-22T16:31:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 348,
      "rating_method": "sequential_elo",
      "raw_elo": 1257.316022774441,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 23.202887647175736,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:cohere-north-mini-code:4a23759df70ab26b",
      "capped_draws": 98,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 106,
      "draws": 98,
      "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": 105,
      "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": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1263.538009086365,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 23.07648794314826,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.387218039620898,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5:3bb27dbc092c7ff2",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:11:21Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1257.9362460272719,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 22.173830070391556,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:inclusionai-ling-3-0-flash:20c76d20ae9b2569",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 15,
      "draws": 34,
      "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": 107,
      "max_score": null,
      "measured_at": "2026-08-20T01:50:48Z",
      "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": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1249.214707380887,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.956639805537932,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.068787932399015,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-luna:fd12531a88a47fab",
      "capped_draws": 30,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 30,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:59:46Z",
      "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": 99,
      "rating_method": "sequential_elo",
      "raw_elo": 1231.2408205466734,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "None (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.58077943551401,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.25,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 91,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-luna:15a0f0a09f9eb8e5",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 68,
      "max_score": null,
      "measured_at": "2026-08-23T12:40:55Z",
      "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": 91,
      "rating_method": "sequential_elo",
      "raw_elo": 1231.009568848009,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "None (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.385298777703543,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.378603514268699,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 176,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:openai-gpt-oss-120b:7785ef5b91a441ff",
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 70,
      "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": "openai/gpt-oss-120b",
        "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": 113,
      "max_score": null,
      "measured_at": "2026-08-22T09:27:15Z",
      "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": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1217.332032382236,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.17906841539228,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 142,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:thinkingmachines-inkling:281eafa14f6ff011",
      "capped_draws": 53,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 53,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 83,
      "max_score": null,
      "measured_at": "2026-08-23T09:56:43Z",
      "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": 1200.6961116510595,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 17.155695255029734,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:xiaomi-mimo-v2-5:024b37c390436d5a",
      "capped_draws": 41,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "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": "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": 29,
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1213.1687467409479,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 17.065325253973946,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-7-max:fa240f0afd3eda59",
      "capped_draws": 30,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 30,
      "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": 54,
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1196.0815382797539,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 15.965232157159793,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 190,
      "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": 92,
      "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": 129,
      "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": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1175.0071677189458,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 13.75796311182292,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.9734349083065625,
      "unilateral_faults": 2,
      "wins": 33
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:thinkingmachines-inkling:a1a9848a1d14b67e",
      "capped_draws": 84,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 109,
      "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": "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": 124,
      "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": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1159.2375706062403,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 12.59254361838801,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.6751283820590555,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "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": 41,
      "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": 62,
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1165.3075653397077,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 12.522239497043625,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:mistralai-mistral-medium-3-5:54288de170df8ebb",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "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": "mistralai/mistral-medium-3-5",
        "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": 63,
      "max_score": null,
      "measured_at": "2026-08-05T03:16:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1152.0261703164747,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 11.379446013072632,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-1-flash-lite:f12274812b7e4c60",
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 45,
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1144.1569784358514,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 10.214928346057336,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 166,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:o3:29970c6bc7db3c37",
      "capped_draws": 48,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 48,
      "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": 111,
      "max_score": null,
      "measured_at": "2026-08-20T02:24:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1105.068326196998,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 7.743053185185025,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 68,
      "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": 31,
      "draws": 13,
      "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": 0,
      "max_score": null,
      "measured_at": "2026-08-23T09:27:52Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1827.6494148740956,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-6-sol:683e7f269aa1d12e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:16:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1817.1768615381052,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "XHigh (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 99.04634600393882,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "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": 36,
      "draws": 32,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "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": 5,
      "max_score": null,
      "measured_at": "2026-08-05T02:22:25Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1739.7423942603561,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 81.45539006883097,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-fable-5:9765333017ba86fe",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 37,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:25:18Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1705.9057480073943,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 73.74954635252826,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2,
      "attempted_matches": 118,
      "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": 45,
      "draws": 38,
      "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": 21,
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1698.998209186365,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 70.34600839013916,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-fable-5:99e7b840e9269907",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 31,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T02:44:38Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1685.6539281264988,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 68.84186917568367,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 2,
      "wins": 38
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 186,
      "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": 93,
      "draws": 76,
      "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": 14,
      "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": 186,
      "rating_method": "sequential_elo",
      "raw_elo": 1654.4005500316935,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 62.66869493063295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 96
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 152,
      "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": 76,
      "draws": 68,
      "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": 16,
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1652.4738991796207,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 61.26562064904274,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-4:00c166645bf94fd4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 51,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:25:22Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1621.61381435049,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "XHigh (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.7169870956697,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "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": 30,
      "draws": 40,
      "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": 1,
      "max_score": null,
      "measured_at": "2026-08-22T14:35:05Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1623.7312204453247,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.238717509734094,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 144,
      "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": 53,
      "draws": 72,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 24,
      "max_score": null,
      "measured_at": "2026-08-23T09:27:52Z",
      "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": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1594.752196706652,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 51.08735602238606,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-6-terra:75cc7f062ffaf091",
      "capped_draws": 0,
      "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": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:16:44Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1584.5440638410278,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.84121932685183,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-6-sol:db6839ea2087dc79",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "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-5.6-sol",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T04:42:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1581.8188124317824,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.54023061897745,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "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": 37,
      "draws": 45,
      "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": 9,
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1576.1121672722809,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.99378748372811,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2,
      "attempted_matches": 28,
      "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": 14,
      "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": "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": 1,
      "max_score": null,
      "measured_at": "2026-08-23T14:10:11Z",
      "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": 28,
      "rating_method": "sequential_elo",
      "raw_elo": 1595.1315475505453,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.45001529607838,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 85.34944487358055,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-sonnet-5:906c16e3480819c2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 55,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:29:04Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.6295667779777,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (historical request variant 3)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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-variant-3",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh (historical request variant 3)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-3",
        "reasoning_bucket_label": "XHigh (historical request variant 3)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-3"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-3",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.035421839838055,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "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": 30,
      "draws": 63,
      "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": 2,
      "max_score": null,
      "measured_at": "2026-08-23T06:52:36Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1515.1687546699268,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.716112021846637,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 67,
      "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": 31,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 6,
      "max_score": null,
      "measured_at": "2026-08-19T23:36:40Z",
      "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": 67,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.5573026507243,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 28.53778014221482,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.883906259083243,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "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": 30,
      "draws": 55,
      "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": 3,
      "max_score": null,
      "measured_at": "2026-08-15T01:46:36Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.2971744001827,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 28.504507698976763,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-6-terra:0983009cb1ffeee4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 91,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:51:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.4681276807262,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 28.399082893812732,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 127,
      "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": 50,
      "draws": 113,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-08-23T03:23:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 127,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.590095915884,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 27.457151552126646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "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": 37,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 11,
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.3343523013145,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 27.437307852969795,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "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": 38,
      "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": "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": 8,
      "max_score": null,
      "measured_at": "2026-08-15T01:45:06Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.463385992254,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.879776376230204,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "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": 30,
      "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-5.6-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": 5,
      "max_score": null,
      "measured_at": "2026-08-23T03:03:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.5055646014496,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "None (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.738936634036737,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "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": 49,
      "draws": 69,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "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": 16,
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.6220047983245,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.601192408895606,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "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": 31,
      "draws": 58,
      "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": 3,
      "max_score": null,
      "measured_at": "2026-08-22T08:14:35Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.3602776554874,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.392941660287374,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-6-sol:7aebae84d73affb6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "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-5.6-sol",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:05:53Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.8193553515018,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "None (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.199687374521076,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-6-terra:08cc40e91e1568bf",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 76,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T10:43:21Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.4957620772557,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 25.970772760443374,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:google-gemini-3-5-flash:5712a3e29dc27925",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "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": "google/gemini-3.5-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": 10,
      "max_score": null,
      "measured_at": "2026-08-03T01:05:13Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.007826929545,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 25.82657411049858,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 77,
      "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": 34,
      "draws": 68,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "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": 4,
      "max_score": null,
      "measured_at": "2026-08-19T21:54:48Z",
      "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": 77,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.0766723506626,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 25.561074219037017,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.86385170722978,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "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": 47,
      "draws": 78,
      "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": 11,
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.645381413465,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 25.52082770903801,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 41,
      "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": "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": 11,
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.18525311898,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 25.441748388952313,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "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": 39,
      "draws": 66,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-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": "2026-08-03T08:48:42Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.2790874838233,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 25.222210730949445,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 102,
      "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": 50,
      "draws": 90,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 10,
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.3681592549508,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 24.925858625367727,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "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": 40,
      "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": "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": "2026-08-04T23:04:52Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.2151308299296,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 23.986859461426256,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-sonnet-5:3d227889fd8fad8f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 81,
      "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": "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": 10,
      "max_score": null,
      "measured_at": "2026-08-05T04:33:12Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.840389816271,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking 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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Thinking disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 23.76930952639686,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 130,
      "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": 49,
      "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": "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": 12,
      "max_score": null,
      "measured_at": "2026-08-15T01:44:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.3344994862955,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 23.676197661918458,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 106,
      "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": 41,
      "draws": 101,
      "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": 3,
      "max_score": null,
      "measured_at": "2026-08-15T01:43:34Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.8316916886058,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 23.401496235109175,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 56,
      "draws": 91,
      "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": 23,
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.596618403244,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 23.349084470138546,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "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": 39,
      "draws": 81,
      "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": 4,
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.3725891120614,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 23.250211486876427,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1,
      "attempted_matches": 154,
      "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": 57,
      "draws": 136,
      "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": 10,
      "max_score": null,
      "measured_at": "2026-08-19T23:37:33Z",
      "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": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.0575574041725,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 22.900288191407675,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 86,
      "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": 41,
      "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": "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": 9,
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.1857236712685,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 22.759457008176497,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1,
      "attempted_matches": 107,
      "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": 41,
      "draws": 105,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 2,
      "max_score": null,
      "measured_at": "2026-08-22T08:45:19Z",
      "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": 107,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.044979547752,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 22.367578645782174,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.362522432468809,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:deepseek-deepseek-v4-flash:1ebaee0e9d08b232",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "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": "deepseek/deepseek-v4-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": 11,
      "max_score": null,
      "measured_at": "2026-08-05T01:25:13Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.442621444907,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 22.300174477766653,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 138,
      "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": 54,
      "draws": 125,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-08-19T21:55:39Z",
      "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": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.4846616121374,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 22.143649514386354,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 86,
      "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": 43,
      "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-5.5",
        "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": "2026-08-04T23:05:09Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.225904404823,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 22.09524395964808,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-sonnet-5:e2e304f6cedf7237",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 73,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:17:03Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.5961079238732,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 21.927203253446606,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:deepseek-deepseek-v4-pro:a4cf9c7798e0d7dc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 80,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T15:08:17Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.8446177830178,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 21.894015414373516,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "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": 38,
      "draws": 77,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-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": 3,
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.7131921870432,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 21.854529388279282,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:openai-gpt-oss-120b:f9a4cf175428ff96",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 77,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:15:41Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.9362990217546,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 21.805843612607568,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 44,
      "draws": 86,
      "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": 3,
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.922484272434,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 21.669541208427077,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 126,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-07-31T03:33:27Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.5630393063643,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 21.658118916144787,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.461902543922633,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 43,
      "draws": 84,
      "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": 3,
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.1832965878284,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 21.626339283900553,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2,
      "attempted_matches": 236,
      "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": 85,
      "draws": 225,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 9,
      "max_score": null,
      "measured_at": "2026-08-23T03:23:43Z",
      "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": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.1384095012668,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 21.191551614417335,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.279970601756496,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "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": 31,
      "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": "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": 2,
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.5240632772964,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 20.925483752639348,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2,
      "attempted_matches": 168,
      "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": 78,
      "draws": 153,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 10,
      "max_score": null,
      "measured_at": "2026-07-31T01:17:54Z",
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.5551920135836,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 20.70201896114623,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.527724777936779,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "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": 37,
      "draws": 58,
      "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": 16,
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.072947000906,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 20.557432544949897,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 17,
      "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": 9,
      "draws": 13,
      "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": 1,
      "max_score": null,
      "measured_at": "2026-08-23T05:29:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.2581453563312,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 20.442652389870492,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 74.10113019775793,
      "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:gpt-5-6-luna:f9f63ab67ac1da8b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 75,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T11:50:52Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.0307143374596,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "XHigh (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 20.364907326166584,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-6-luna:fd12531a88a47fab",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 84,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:06:03Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.444458797462,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "None (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 20.124599730294026,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 124,
      "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": 43,
      "draws": 111,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-08-22T14:35:05Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.031259226249,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.990967262210003,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "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": 48,
      "draws": 83,
      "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": 13,
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.125463708624,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.847233163024622,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 39,
      "draws": 79,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 18,
      "max_score": null,
      "measured_at": "2026-08-22T07:54:09Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.9653251764248,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.758668893473487,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 86,
      "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": 42,
      "draws": 84,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 2,
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.998408715422,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.57568162564367,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 66,
      "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": 33,
      "draws": 65,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.8584606204145,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.548028827872443,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 256,
      "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": 97,
      "draws": 234,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-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": 20,
      "max_score": null,
      "measured_at": "2026-08-22T08:45:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.157553055973,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.535834131740515,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.3089127354028465,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-6-luna:89e8232b6c428839",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "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-5.6-luna",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T09:30:03Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.7463855821793,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.534394534685426,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 138,
      "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": 68,
      "draws": 118,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 18,
      "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": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.6237702694034,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.283288670132,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:deepseek-deepseek-v4-flash:865c6d4e9c2ee4b8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 80,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:29:01Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.6834789339953,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.168036379032152,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-4:ef3925c3f5fdbb2d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 70,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T07:00:26Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.1177660210396,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.148888518137927,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 174,
      "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": 87,
      "draws": 156,
      "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": 14,
      "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": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.5162308159042,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.073029071771302,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.552760371103872,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-4:c42a41ea59ccc1f7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 81,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:33:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.7295454760624,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "None (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.06652602077495,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1,
      "attempted_matches": 64,
      "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": 32,
      "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": "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.1999436475344,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.008405115879473,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 106,
      "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": 52,
      "draws": 99,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 4,
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.0890590046167,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 18.971051988167996,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "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": 50,
      "draws": 94,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.7390320719044,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 18.862874029135362,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "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": 43,
      "draws": 72,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 12,
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.2386314581393,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 18.7319500025143,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "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": 37,
      "draws": 68,
      "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": 5,
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.7697346783725,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 18.694108648166214,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "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": 32,
      "draws": 61,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-23T03:04:42Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.6081174048713,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking 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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Thinking disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 18.458780422070696,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "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": 30,
      "draws": 62,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-08-23T06:52:36Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.1243014745253,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 18.196918446623908,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 45,
      "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": "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": 1,
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.658322014426,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 17.570880513249598,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "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": 31,
      "draws": 61,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "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": 10,
      "max_score": null,
      "measured_at": "2026-08-22T07:54:09Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.3461864208352,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "None (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 17.424895818830112,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 44,
      "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": "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": 5,
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.1606606288503,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 17.357469503708607,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 252,
      "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": 94,
      "draws": 229,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-08-23T03:03:24Z",
      "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": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.4683467098837,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 17.072829141107093,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.6667408666858066,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 136,
      "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": 68,
      "draws": 114,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 20,
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.4662368310856,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 16.923785423162606,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.461902543922633,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 47,
      "draws": 110,
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.7308308182332,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 16.871313010451086,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1,
      "attempted_matches": 72,
      "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": 35,
      "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": "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": 3,
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.210402384003,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 16.721194515766282,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "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": 41,
      "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": "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": 11,
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.0500885064464,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 16.55738720588751,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "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": 31,
      "draws": 57,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-19T21:57:00Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.6017691862596,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 16.50878695816217,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "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": 39,
      "draws": 72,
      "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": 5,
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.7183503047993,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 16.344385607773184,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "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": 44,
      "draws": 82,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.5362643626052,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 16.214567763911244,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 128,
      "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": 64,
      "draws": 118,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 9,
      "max_score": null,
      "measured_at": "2026-07-31T03:32:32Z",
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.8538739796686,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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",
          "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 16.009458011887702,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.289400506511907,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "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": 9,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 0,
      "max_score": null,
      "measured_at": "2026-08-22T09:26:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.6020204364095,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 15.025055106927441,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 70.95786693528086,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "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": 36,
      "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": "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": "2026-07-31T02:27:36Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.8163020312015,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 14.388654431203785,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "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": 31,
      "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-5.6-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": "2026-08-20T02:43:51Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.6966388554522,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "None (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 14.182848437029604,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 20,
      "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": 11,
      "draws": 20,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 0,
      "max_score": null,
      "measured_at": "2026-08-23T00:33:40Z",
      "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": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.2472717904682,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 14.155329190210882,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:openai-gpt-oss-120b:d658f92b65107751",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 59,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:23:18Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.0685143240635,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 13.91305101107773,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 68,
      "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": 32,
      "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": "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": 12,
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.0591535680944,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 13.758406271721789,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 130,
      "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": 50,
      "draws": 107,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-08-19T22:29:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.2065730933373,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 13.32462959183295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 22,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:inclusionai-ling-3-0-flash:20c76d20ae9b2569",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 11,
      "draws": 98,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-08-19T21:57:09Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.556144588857,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 12.133934164094017,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 33.25453326951843,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "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": 10,
      "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": "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": 2,
      "max_score": null,
      "measured_at": "2026-08-20T05:43:08Z",
      "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": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.6963543985923,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 11.78759779354171,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "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": 39,
      "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": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T08:16:45Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.2739821056432,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 11.783172968660383,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1,
      "attempted_matches": 16,
      "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": 9,
      "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-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": 1,
      "max_score": null,
      "measured_at": "2026-08-23T03:04:42Z",
      "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": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.473546162997,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 11.574430248545012,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 42,
      "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": 21,
      "draws": 24,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "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": 11,
      "max_score": null,
      "measured_at": "2026-08-23T14:09:45Z",
      "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": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.162820902962,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 10.098703084006734,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 17,
      "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": 8,
      "draws": 14,
      "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": 3,
      "max_score": null,
      "measured_at": "2026-08-22T08:45:10Z",
      "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": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.545523222252,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 7.491362721335916,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 74.10113019775793,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 42,
      "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": 21,
      "draws": 28,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-08-23T14:09:45Z",
      "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": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.4161473966744,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 3.872072017351666,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 116,
      "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": 50,
      "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": 9,
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1896.2197178100707,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 98.71900811266804,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 107
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 42,
      "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-5.6-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": 6,
      "max_score": null,
      "measured_at": "2026-08-21T15:52:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1868.3709719929363,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 96.368869361455,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 85
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 162,
      "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": 81,
      "draws": 8,
      "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": 15,
      "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": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1867.8291510173494,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 95.92764370282903,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.468842775200363,
      "unilateral_faults": 0,
      "wins": 139
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-6-flash:b4583ef7c04d45cd",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "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": "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": 23,
      "max_score": null,
      "measured_at": "2026-08-22T17:46:24Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1772.0196909880037,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 83.98010770719294,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-fable-5:9765333017ba86fe",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 32,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-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": 7,
      "max_score": null,
      "measured_at": "2026-08-03T14:08:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1699.478327839778,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 72.45110481946428,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:moonshotai-kimi-k3:6a00f2f5a49a8584",
      "capped_draws": 3,
      "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": "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": 21,
      "max_score": null,
      "measured_at": "2026-08-21T11:42:46Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1644.1494064849203,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 66.78378455408968,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 90,
      "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": 42,
      "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-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": 25,
      "max_score": null,
      "measured_at": "2026-08-21T15:52:22Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1642.3853735340704,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 65.52108067097569,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-sol:683e7f269aa1d12e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:16:50Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1625.9039362576423,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "XHigh (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 62.521116224377955,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-sonnet-5:a86621e2793b5dec",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 31,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-08-20T23:23:22Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.9042805271881,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking 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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Thinking disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 61.57727285827689,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-terra:75cc7f062ffaf091",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T22:43:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1614.760774095997,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 60.60474629403735,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-4:c42a41ea59ccc1f7",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 32,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:55:59Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1604.3956609608717,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "None (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 60.07677932346456,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 33
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 272,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-sonnet-5:72c37c305741dafa",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 108,
      "draws": 104,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-21T04:34:53Z",
      "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": 272,
      "rating_method": "sequential_elo",
      "raw_elo": 1579.1406170036207,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "XHigh (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 57.62901429743519,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.902777777777777,
      "unilateral_faults": 0,
      "wins": 99
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 158,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:moonshotai-kimi-k3:f0bfe8c58b2cc988",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "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": "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": 40,
      "max_score": null,
      "measured_at": "2026-08-22T17:46:55Z",
      "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": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1571.4990999527986,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 57.255056886144494,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-sonnet-5:ec6362fd3d2a0220",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 42,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-08-21T05:32:06Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1575.6075710349296,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 56.36010974706571,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-5-flash:5712a3e29dc27925",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "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": "google/gemini-3.5-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": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:19:33Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1577.6092570519809,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 55.84887374161656,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:thinkingmachines-inkling:b27963da4b6944f2",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "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": "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": 37,
      "max_score": null,
      "measured_at": "2026-08-22T12:02:27Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.1129209687915,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.7905686677935,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 2,
      "attempted_matches": 176,
      "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": 88,
      "draws": 35,
      "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": 56,
      "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": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1561.558435222868,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.44510087203772,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.259934288992827,
      "unilateral_faults": 0,
      "wins": 85
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 264,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-5-flash-lite:5943a501fa6113ab",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 97,
      "draws": 61,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 95,
      "max_score": null,
      "measured_at": "2026-08-22T20:25:22Z",
      "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": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1543.7025318084882,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 53.05834174786712,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.48567977499789805,
      "unilateral_faults": 0,
      "wins": 108
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 43,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "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": 36,
      "max_score": null,
      "measured_at": "2026-08-22T17:46:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1549.3266540892673,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.90544213032362,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:meta-muse-spark-1-2:0ef600658249027b",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "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": "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": 30,
      "max_score": null,
      "measured_at": "2026-08-21T11:43:18Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.3955110326083,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.70215835783597,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-sol:db6839ea2087dc79",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "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-5.6-sol",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:53:16Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.5990433024108,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.56973107349277,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-sol:e7389fafab42de55",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "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-5.6-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": 19,
      "max_score": null,
      "measured_at": "2026-08-23T02:31:42Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.3926522758095,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "None (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.50574288116246,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 176,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-5-flash-lite:55634764b9427e4e",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 68,
      "draws": 52,
      "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": 51,
      "max_score": null,
      "measured_at": "2026-08-22T20:29:46Z",
      "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": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1532.6867109455625,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.19326999050381,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:z-ai-glm-5-2:7c1742483386cdf8",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 86,
      "draws": 80,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-22T14:35:20Z",
      "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": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1535.1007128451727,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 51.704133366709385,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3379525022706273,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 324,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-6-flash:b574aaabaed70f28",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 129,
      "draws": 107,
      "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": 90,
      "max_score": null,
      "measured_at": "2026-08-22T17:46:55Z",
      "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": 324,
      "rating_method": "sequential_elo",
      "raw_elo": 1521.8275933200516,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.541598092506504,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 127
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 83,
      "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": 39,
      "draws": 30,
      "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": 29,
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.349657382233,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 49.85325759783324,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "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": 42,
      "draws": 28,
      "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": 31,
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1521.331600253054,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 48.831744011327004,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:meta-muse-spark-1-2:c4024993f2e98d89",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": 34,
      "max_score": null,
      "measured_at": "2026-08-21T11:42:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.9551554503532,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 48.767930985582225,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-4-5:959db58a0f4d59b9",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "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": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:50:27Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1517.64293491248,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 48.527410514780094,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-terra:0983009cb1ffeee4",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 36,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T13:39:17Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1515.2761169916803,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 47.862625672133966,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 168,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:thinkingmachines-inkling:a1a9848a1d14b67e",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 82,
      "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": "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": 37,
      "max_score": null,
      "measured_at": "2026-08-05T05:23:15Z",
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1513.9841261509482,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 47.82588085262712,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.527724777936779,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "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": 27,
      "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": "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": 21,
      "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": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.0961019109775,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 47.63490899953319,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 160,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-4-5:e2ff6744eb1bb7c6",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 77,
      "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": 48,
      "max_score": null,
      "measured_at": "2026-08-21T04:34:57Z",
      "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": 160,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.8789320043286,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 47.38893238646811,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-5-flash:2637a22cd82f12e9",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "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": "google/gemini-3.5-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": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:18:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.688890303186,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 47.29777519993979,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 270,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-6-flash:13a24e3021af753a",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 106,
      "draws": 69,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 113,
      "max_score": null,
      "measured_at": "2026-08-22T11:01:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 270,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.3603963409328,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.93983383805609,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 78,
      "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": 39,
      "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": "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": 26,
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.9890080189186,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.92997006877206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 0,
      "draws": 26,
      "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": 18,
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1513.1510056240777,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.8688872071828,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-sonnet-5:3d227889fd8fad8f",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 36,
      "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": "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": 27,
      "max_score": null,
      "measured_at": "2026-08-05T05:17:07Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1506.3942752497016,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking 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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Thinking disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.796831298958985,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 45,
      "draws": 34,
      "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": 28,
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.4667049734755,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.59618183026941,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:thinkingmachines-inkling-small:c4a079d6b58a2c73",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 8,
      "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": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-22T14:35:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.532411443232,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.53778410260007,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 70.95786693528086,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "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": 44,
      "draws": 41,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 26,
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.2810908524089,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.280998303857686,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 21
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:z-ai-glm-5-2:5ea14bc9644b6a2b",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 58,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T02:51:28Z",
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.8935207156142,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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",
          "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.17948587926281,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.37252890985009,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 142,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:meituan-longcat-2-0:bed5035a5082adf8",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "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": "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": 39,
      "max_score": null,
      "measured_at": "2026-08-21T09:13:52Z",
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.9131306078064,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.134251044046394,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 85,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-4-mini:e296afd987da0af3",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 21,
      "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": 85,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.1394784776523,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.25460249709266,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.16638660171921,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-terra:08cc40e91e1568bf",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "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-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:19:59Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.6473394621028,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.06898280210667,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "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": 42,
      "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-5.4-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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.8658260094098,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 42.50170870197985,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-luna:e05ef4cc93414f96",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 39,
      "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": 32,
      "max_score": null,
      "measured_at": "2026-08-22T12:02:27Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.744367648308,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 42.41087590952312,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 25,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:stealth-ox-alpha:6719f8157bcde29f",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 12,
      "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": "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": 6,
      "max_score": null,
      "measured_at": "2026-08-23T14:10:38Z",
      "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": 24,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.4080832752197,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.818965805599504,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 94.92504905630729,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 17,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03: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": 9,
      "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-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": 7,
      "max_score": null,
      "measured_at": "2026-08-22T21:12:16Z",
      "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": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.0917022516862,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.72942915084835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 74.10113019775793,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-4:672219b99ff5a80c",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "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-5.4",
        "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": 26,
      "max_score": null,
      "measured_at": "2026-08-23T08:23:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.4947162156686,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.54480799633329,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-luna:fd12531a88a47fab",
      "capped_draws": 1,
      "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": "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:24:36Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.7893639049173,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "None (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.31733999385539,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:minimax-minimax-m3:6639861dd7b73e51",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "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": "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": 26,
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.257046359489,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.31640418901639,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 158,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:x-ai-grok-4-5:5e133fd8ec34ed0c",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "draws": 68,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 56,
      "max_score": null,
      "measured_at": "2026-08-22T23:22:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.345041387723,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.15892215398935,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 16,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03: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": 9,
      "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": "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": 4,
      "max_score": null,
      "measured_at": "2026-08-22T11:01:47Z",
      "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": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.121643907326,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.08868410464794,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:thinkingmachines-inkling:281eafa14f6ff011",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 50,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-08-23T03:05:15Z",
      "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": 1455.6626650012568,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.92223596271898,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-luna:89e8232b6c428839",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 44,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:11:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.3304554695912,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.4123073013434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 17,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03: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": 9,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 5,
      "max_score": null,
      "measured_at": "2026-08-21T15:54:27Z",
      "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": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.8258524700977,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.330911797900164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 74.10113019775793,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-sonnet-5:73f1b29a5c45562d",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 31,
      "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": 36,
      "max_score": null,
      "measured_at": "2026-08-22T14:30:42Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.2008449551374,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.02092072410418,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 251,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:poolside-laguna-s-2-1:533b6103a5973424",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 112,
      "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": "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": 77,
      "max_score": null,
      "measured_at": "2026-08-22T23:51:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 251,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.4006292034796,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.927445639857304,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 77,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03: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": 34,
      "draws": 29,
      "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": 30,
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.2318976814317,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.527524812029206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 1,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 152,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-4-5:9f0371e603fb81bd",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 41,
      "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": 64,
      "max_score": null,
      "measured_at": "2026-08-21T05:32:06Z",
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.6013043122741,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.20269156862466,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 136,
      "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": 47,
      "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": "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": 55,
      "max_score": null,
      "measured_at": "2026-08-22T21:12:16Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.0846957731926,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.84780628544275,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 16,
      "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": 9,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 5,
      "max_score": null,
      "measured_at": "2026-08-23T02:31:42Z",
      "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": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.4910334028175,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.823095003355,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "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": 43,
      "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": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:49:50Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.882558264278,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.551433143204484,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:moonshotai-kimi-k3:ccf8a3c1c9260d55",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 35,
      "max_score": null,
      "measured_at": "2026-08-22T13:52:12Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.701374575963,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.53169274626354,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:36d8ebdcb946256c",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 41,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 15,
      "max_score": null,
      "measured_at": "2026-08-05T05:17:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.8646223820033,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.40303950625073,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-sol:7aebae84d73affb6",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 42,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:37:58Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.8744235238303,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "None (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.34519124591633,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 93,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-luna:29e28a5adce9180a",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-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": 44,
      "max_score": null,
      "measured_at": "2026-08-23T05:19:28Z",
      "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": 93,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.308968688837,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.22032267709648,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.821062312939668,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 281,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-5-flash-lite:0bab1c3ea19c7cb7",
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 103,
      "draws": 119,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 109,
      "max_score": null,
      "measured_at": "2026-08-23T08:23:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 281,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.9985313839934,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.12765176299469,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:nex-agi-nex-n2-pro:b04b6e7c11ec4633",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "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": "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": 15,
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.1051582810692,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.07029226565205,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 95,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03: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": 42,
      "draws": 28,
      "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": 31,
      "max_score": null,
      "measured_at": "2026-08-21T11:43:42Z",
      "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": 95,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.5396369864504,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.03814073039753,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.281036307982882,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-4-8:8ccf8977401d94db",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "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-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": 15,
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.7477631553459,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.68653930194108,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 11
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 39,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03: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": 18,
      "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": "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": 8,
      "max_score": null,
      "measured_at": "2026-08-23T15:12:59Z",
      "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": 35,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.2407303398938,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.63978744841054,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 96.61669937087152,
      "unilateral_faults": 4,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-4:00c166645bf94fd4",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "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-5.4",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T03:30:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.9639269862823,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "XHigh (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.49790231061323,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 2,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "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": 41,
      "draws": 36,
      "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": 28,
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.1973645808223,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.29934502959449,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-5:1a25631bf54a6363",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "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-5.5",
        "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": 24,
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.9850240219848,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.041752080817375,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:deepseek-deepseek-v4-flash:865c6d4e9c2ee4b8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "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": "deepseek/deepseek-v4-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": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:23:15Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.6399776232663,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.61116549844097,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:z-ai-glm-5-2:f14efcbac580ffaa",
      "capped_draws": 15,
      "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": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T02:57:05Z",
      "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": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.1124041249502,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.602494823476015,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-4:ef3925c3f5fdbb2d",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "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-5.4",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T06:55:12Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.6751894818985,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.41082871103601,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:qwen-qwen3-7-max:a92ef5f3c3f212e3",
      "capped_draws": 6,
      "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": "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": 10,
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.0472522295584,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.201572417188274,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2,
      "attempted_matches": 318,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:poolside-laguna-s-2-1:07eac22bdea1b9b3",
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 117,
      "draws": 133,
      "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": 123,
      "max_score": null,
      "measured_at": "2026-08-23T03:05:15Z",
      "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": 318,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.9195777629861,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.84632546230651,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:nex-agi-nex-n2-pro:a8c61d4550659ad0",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 35,
      "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": 27,
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.8192171011551,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.022102828158765,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "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": 33,
      "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": "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": 20,
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.5993597267618,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 33.32639046166839,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:openai-gpt-oss-120b:f9a4cf175428ff96",
      "capped_draws": 8,
      "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": "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:30:48Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.558557661116,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.858125032877226,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:deepseek-deepseek-v4-pro:a4cf9c7798e0d7dc",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T22:38:18Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.1567925431275,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.83797916630326,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "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": 31,
      "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",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:53:39Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.0902606081052,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.739075020104682,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:cohere-north-mini-code:959513c67c4e5ee3",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 28,
      "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": 24,
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.0627821631542,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.765006071781528,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 44.67073949561819,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 15,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:qwen-qwen3-8-max:a791831295f0ee80",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "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": "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": 7,
      "max_score": null,
      "measured_at": "2026-08-22T20:29:46Z",
      "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": 15,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.2371045770194,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.071719571532732,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 81.25,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:be72f75fe8d3007b",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "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": "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": 9,
      "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": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1393.790497688098,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.736891928612994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 166,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:meituan-longcat-2-0:45102822fc5f9296",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 79,
      "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": "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": 54,
      "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": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1380.8913638836275,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.66163798427531,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.830591148722647,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 28,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:stealth-ox-alpha:dfb3dd7361cfa1a2",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 12,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 10,
      "max_score": null,
      "measured_at": "2026-08-23T15:12:59Z",
      "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": 23,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.2308212149396,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.634239899442424,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 97.46252452815364,
      "unilateral_faults": 1,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-4:cea8a68bd875deb9",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "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-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": 34,
      "max_score": null,
      "measured_at": "2026-08-21T11:43:42Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1371.9311932402272,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "None (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 28.856580393425084,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 200,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:inclusionai-ling-3-0-flash:1ed2a890413ad375",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 79,
      "draws": 87,
      "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": 77,
      "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": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1361.644886820065,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 27.56514642169852,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.00917733558763,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-luna:f9f63ab67ac1da8b",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "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-5.6-luna",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T22:43:00Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1366.0934547211268,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "XHigh (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 27.034062861276098,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-luna:15a0f0a09f9eb8e5",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 51,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 40,
      "max_score": null,
      "measured_at": "2026-08-23T05:19:28Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1347.201035529736,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "None (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 25.42965253398741,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 152,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:openai-gpt-oss-120b:7785ef5b91a441ff",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 63,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 78,
      "max_score": null,
      "measured_at": "2026-08-22T23:51:52Z",
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1273.1146500874393,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 16.522204329731178,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-sonnet-5:906c16e3480819c2",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "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-sonnet-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": 38,
      "max_score": null,
      "measured_at": "2026-08-03T14:16:27Z",
      "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": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1285.3975984985518,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (historical request variant 3)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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-variant-3",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh (historical request variant 3)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-3",
        "reasoning_bucket_label": "XHigh (historical request variant 3)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-3"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-3",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 15.623941414360715,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 162,
      "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": 64,
      "draws": 42,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 111,
      "max_score": null,
      "measured_at": "2026-08-22T17:42:01Z",
      "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": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1150.82535220259,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-fable-5:9765333017ba86fe",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "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-fable-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": 5,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:18Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1871.3393976382893,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "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": 36,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-22T05:58:30Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1810.5520082026756,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 89.87612305774321,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "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": 36,
      "draws": 11,
      "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": 3,
      "max_score": null,
      "measured_at": "2026-08-22T06:40:40Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1802.997606042514,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 88.72393191119036,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 64
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 164,
      "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": 68,
      "draws": 26,
      "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": 19,
      "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": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1769.8664441103872,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 83.8367732821356,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.144085005109797,
      "unilateral_faults": 0,
      "wins": 119
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 152,
      "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": 58,
      "draws": 47,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 19,
      "max_score": null,
      "measured_at": "2026-08-22T06:50:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1735.222095654677,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 80.31858860898552,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-6-sol:683e7f269aa1d12e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 44,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:05:16Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1661.9721859570288,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "XHigh (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 67.94724948155005,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "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": 42,
      "draws": 37,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1645.9101696696405,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 65.49748409048952,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-4:00c166645bf94fd4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 36,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:05:07Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1637.1951751819909,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "XHigh (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 64.10539152692174,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 36
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 305,
      "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": 115,
      "draws": 77,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "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": 90,
      "max_score": null,
      "measured_at": "2026-08-23T12:51:05Z",
      "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": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1595.56223467484,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 58.999575365642215,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 85,
      "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": 37,
      "draws": 43,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "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": 4,
      "max_score": null,
      "measured_at": "2026-08-22T04:12:35Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1602.7644735229496,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 58.3519781342059,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "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": 36,
      "draws": 40,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-22T06:51:00Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1602.2107727942875,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 57.919430982158175,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "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": 51,
      "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": "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": 24,
      "max_score": null,
      "measured_at": "2026-08-05T05:32:31Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1584.2614626043232,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 56.21511165223179,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-fable-5:99e7b840e9269907",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 33,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:23:59Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1582.2001981056562,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 55.133363671974216,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-6-terra:75cc7f062ffaf091",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 44,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:35:30Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1568.1292217619282,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 53.506645149871794,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04: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": 46,
      "draws": 51,
      "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": 23,
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1566.3530638646457,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 53.300611514890754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "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": 46,
      "draws": 64,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-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": 9,
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1562.2888242629197,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.743625903198904,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 25
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 206,
      "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": 103,
      "draws": 90,
      "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": 57,
      "max_score": null,
      "measured_at": "2026-08-05T05:03:35Z",
      "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": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.023551151262,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.394609038466754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.280733777820661,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 45,
      "draws": 61,
      "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": 9,
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.7577793037303,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.09375303448146,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemini-3-5-flash:5712a3e29dc27925",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:04:12Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.5455372468282,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 51.31859933665385,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 27
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 204,
      "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": 102,
      "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": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:33:21Z",
      "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": 204,
      "rating_method": "sequential_elo",
      "raw_elo": 1550.6547495671625,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 51.08859351407519,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "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": 39,
      "draws": 50,
      "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": 14,
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.6081087252508,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.534733628873596,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "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": 11,
      "draws": 10,
      "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": 1,
      "max_score": null,
      "measured_at": "2026-08-23T12:51:05Z",
      "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": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1594.1909851365033,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.427853739274326,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-sonnet-5:906c16e3480819c2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 54,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:29:31Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1534.9415708206361,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (historical request variant 3)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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-variant-3",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh (historical request variant 3)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-3",
        "reasoning_bucket_label": "XHigh (historical request variant 3)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-3"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-3",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 48.16343828710374,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-6-sol:db6839ea2087dc79",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 86,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:03:35Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1524.9887263647072,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 47.3426724694463,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 156,
      "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": 63,
      "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": "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": 31,
      "max_score": null,
      "measured_at": "2026-08-23T04:48:24Z",
      "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": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.343293683398,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.69357274580004,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-6-terra:0983009cb1ffeee4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "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-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:20:19Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1521.160171149716,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.206877878735085,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "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": 47,
      "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": "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": 11,
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.32655258939,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.03853672066733,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 11
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 264,
      "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": 101,
      "draws": 163,
      "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": 45,
      "max_score": null,
      "measured_at": "2026-08-23T01:51:58Z",
      "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": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.2420234775436,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.281108867143885,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.13627265814059708,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-6-terra:08cc40e91e1568bf",
      "capped_draws": 0,
      "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": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:15:06Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.6341572765252,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.865298973012386,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 17,
      "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": 8,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 1,
      "max_score": null,
      "measured_at": "2026-08-22T17:44:30Z",
      "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": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1562.2633173996858,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.49159171005959,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 74.10113019775793,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-4:ef3925c3f5fdbb2d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "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",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:15:01Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.7163572188297,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.235477379188055,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-sonnet-5:3d227889fd8fad8f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 69,
      "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": "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": "2026-08-05T05:33:43Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.157122022894,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking 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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Thinking disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.23081556016269,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "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": 36,
      "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": "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": 13,
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1506.6569734340017,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.249796081077825,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 15
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 154,
      "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": 77,
      "draws": 100,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 29,
      "max_score": null,
      "measured_at": "2026-07-31T02:43:08Z",
      "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": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.1231788792588,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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",
          "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.08531679812856,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.951351796455231,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-6-luna:89e8232b6c428839",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 87,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T10:44:00Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.8994434966728,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 42.465453488707176,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-6-sol:7aebae84d73affb6",
      "capped_draws": 0,
      "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": "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:17:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.3796453332363,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "None (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 42.431290788636126,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 43,
      "draws": 77,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 5,
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.6174746882057,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 42.15860784753806,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 2,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "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": 47,
      "draws": 66,
      "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": 23,
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.791657928284,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 42.07260490289768,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "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": 37,
      "draws": 54,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-08-22T13:00:23Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.2951959311706,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "None (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.80833395633762,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 13
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "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": 24,
      "draws": 17,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-08-23T12:27:48Z",
      "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": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.063493316194,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.756439517176496,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 137,
      "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": 53,
      "draws": 94,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 17,
      "max_score": null,
      "measured_at": "2026-08-22T06:51:00Z",
      "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": 133,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.9182974099629,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.65185972817385,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-6-luna:f9f63ab67ac1da8b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 44,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:29:50Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.9345388012882,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "XHigh (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.6040414636828,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 62,
      "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": 31,
      "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": "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": 7,
      "max_score": null,
      "measured_at": "2026-07-31T02:30:53Z",
      "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": 1498.4721260722356,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.455613711503254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 47,
      "draws": 66,
      "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": 18,
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.1646241939861,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.222856430705775,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 41,
      "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": "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": 20,
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.643674866353,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.94245051776638,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "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": 36,
      "draws": 44,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-08-21T20:36:03Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.4637763376538,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking 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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Thinking disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.87587184385918,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "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": 48,
      "draws": 62,
      "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": 21,
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.6589592065263,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.81207563674785,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-sonnet-5:e2e304f6cedf7237",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 72,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:04:02Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.2172580461772,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.6514142799952,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "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": 34,
      "draws": 52,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 10,
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.8209858823616,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.63045169882911,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-4:c42a41ea59ccc1f7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 71,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T23:35:32Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.8733493227608,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "None (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.51992276550704,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 134,
      "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": 53,
      "draws": 84,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-08-22T23:41:33Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.2686847664681,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.504702920191605,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 92,
      "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": 44,
      "draws": 76,
      "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": 9,
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.269501274785,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.496965218840195,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 110,
      "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": 54,
      "draws": 82,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 16,
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.3694583369315,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.43774279100727,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "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": 33,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 10,
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.7254504864673,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.35454880564338,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 46,
      "draws": 84,
      "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": 7,
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.7467967975713,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.244014723647986,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "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": 45,
      "draws": 102,
      "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": 7,
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.192389292363,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.10360954415184,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 51,
      "draws": 76,
      "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": 16,
      "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": 103,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.6181811749257,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.978937009585955,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.279033784546012,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 280,
      "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": 106,
      "draws": 218,
      "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": 40,
      "max_score": null,
      "measured_at": "2026-08-23T13:45:16Z",
      "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": 280,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.01042909638,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.81555278408415,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 76,
      "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": 36,
      "draws": 54,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-08-22T06:51:04Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.7694515360909,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.7944295068769,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "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": 41,
      "draws": 60,
      "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": 15,
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.1348689981835,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.727863503836645,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "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": 51,
      "draws": 63,
      "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": 17,
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.5304118625747,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.63154205082826,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "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": 43,
      "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": "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": 9,
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.369156952384,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.60896936866197,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 144,
      "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": 72,
      "draws": 113,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 10,
      "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": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.5782235231818,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.57531415912807,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.787054914327616,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "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": 47,
      "draws": 90,
      "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": 12,
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.3257249175822,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.56123446848897,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:openai-gpt-oss-120b:d658f92b65107751",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "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": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:11:31Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.2518107556666,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.431761090888465,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "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": 46,
      "draws": 68,
      "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": 19,
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.7924746051574,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.423521122325184,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-6-luna:fd12531a88a47fab",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 68,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:33:43Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.7905244904262,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "None (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.21567848608893,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 49,
      "draws": 87,
      "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": 12,
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.653364825019,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.94522426719343,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 113,
      "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": 15,
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.6624992252573,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.871593758786716,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.65987454855759,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 253,
      "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": 111,
      "draws": 195,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-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": 31,
      "max_score": null,
      "measured_at": "2026-08-22T14:13:36Z",
      "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": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.3565254548685,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.573622197421955,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.7477795630767012,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "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": 36,
      "draws": 46,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-22T11:33:38Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.7287106223077,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.1105048676341,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 15,
      "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": 8,
      "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": "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": 0,
      "max_score": null,
      "measured_at": "2026-08-21T20:01:27Z",
      "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": 15,
      "rating_method": "sequential_elo",
      "raw_elo": 1525.0357629986581,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.941404265071526,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 81.25,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 47,
      "draws": 83,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 8,
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.340110846728,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.74168060162787,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "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": 36,
      "draws": 61,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.91418843072,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.7416657545222,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "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": 33,
      "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": "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": 9,
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.9778216962018,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.49517602497302,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 92,
      "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": 40,
      "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": "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": 6,
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.0389711785886,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.342280705591044,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 2,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 44,
      "draws": 65,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 19,
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.9284785190819,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.17290928698389,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 186,
      "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": 87,
      "draws": 129,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 45,
      "max_score": null,
      "measured_at": "2026-07-31T02:43:24Z",
      "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": 186,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.0591159526518,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.98827123707588,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.840775046388435,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 44,
      "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-5.4-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": 16,
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.0297776195794,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.883321001904825,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 46,
      "draws": 94,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 19,
      "max_score": null,
      "measured_at": "2026-08-22T11:33:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.3921381611772,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.872662603409985,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "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": 38,
      "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-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": 15,
      "max_score": null,
      "measured_at": "2026-08-22T06:51:04Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.346288772209,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "None (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.463037436242594,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:deepseek-deepseek-v4-pro:d03a9ec0db9a8b52",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "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": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:11:41Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.4828868208863,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.42341278591467,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 255,
      "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": 114,
      "draws": 188,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 37,
      "max_score": null,
      "measured_at": "2026-08-21T20:33:16Z",
      "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": 255,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.1461491938412,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.37827885826509,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.042462425705284,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "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": 42,
      "draws": 66,
      "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": 14,
      "max_score": null,
      "measured_at": "2026-08-05T05:32:45Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.7387499700872,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.31202602070684,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 273,
      "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": 107,
      "draws": 171,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 66,
      "max_score": null,
      "measured_at": "2026-08-22T23:41:33Z",
      "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": 272,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.685284464945,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.183653647643865,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:openai-gpt-oss-120b:f9a4cf175428ff96",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 83,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:14:37Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.7004190221962,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.96640446666731,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 159,
      "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": 60,
      "draws": 83,
      "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": 59,
      "max_score": null,
      "measured_at": "2026-08-22T04:11:45Z",
      "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": 159,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.887567292159,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.688547830022806,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 178,
      "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": 87,
      "draws": 124,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 32,
      "max_score": null,
      "measured_at": "2026-08-05T05:32:49Z",
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.3475549764407,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.67352159482515,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.9766057392055,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "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": 42,
      "draws": 67,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 12,
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.4224780953568,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.65160344774605,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 9
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "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": 24,
      "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": "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": 9,
      "max_score": null,
      "measured_at": "2026-08-23T12:27:48Z",
      "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": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.2014764650874,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.0666411169392,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "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": 36,
      "draws": 58,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-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": 11,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:21Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.8487821616854,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.25188976239682,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:cohere-north-mini-code:959513c67c4e5ee3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 32,
      "draws": 81,
      "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": 18,
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.3736279368563,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 33.52310753913016,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 25.383326230453278,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemini-3-5-flash:2637a22cd82f12e9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "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": "google/gemini-3.5-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": 38,
      "max_score": null,
      "measured_at": "2026-08-05T05:04:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.4852159713996,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 33.44484317358223,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 133,
      "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": 51,
      "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": "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": 21,
      "max_score": null,
      "measured_at": "2026-08-23T13:45:16Z",
      "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": 133,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.310826299396,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 33.17065439419427,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 102,
      "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": 49,
      "draws": 79,
      "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": 15,
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.1215027312614,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.85833209398961,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:inclusionai-ling-3-0-flash:20c76d20ae9b2569",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 25,
      "draws": 129,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-08-22T04:21:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.6985624189183,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.370699474354865,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.984274827972971,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 154,
      "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": 59,
      "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": "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": 54,
      "max_score": null,
      "measured_at": "2026-08-23T02:43:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.3352985192469,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.171720342982304,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 86,
      "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": 42,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 19,
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.305372108474,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.89937377831447,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "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": 10,
      "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": "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": 5,
      "max_score": null,
      "measured_at": "2026-08-23T08:02:59Z",
      "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": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.3700914144779,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.39027464270986,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "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": 8,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-21T20:10:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.637623633983,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.86262516391439,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 22,
      "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": 11,
      "draws": 17,
      "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": 4,
      "max_score": null,
      "measured_at": "2026-08-23T01:51:58Z",
      "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": 22,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.4779270736012,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.32099723181149,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 60.5072070285374,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 83,
      "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": 37,
      "draws": 42,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 29,
      "max_score": null,
      "measured_at": "2026-08-22T04:12:04Z",
      "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": 83,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.712515509699,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "None (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.16798634189743,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.804472558998102,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "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": 36,
      "draws": 44,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:21Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.4061831629094,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.06636734322581,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "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": 36,
      "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": "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": 27,
      "max_score": null,
      "measured_at": "2026-08-22T06:20:10Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.1381799035316,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 28.86928741865205,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "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": 42,
      "draws": 45,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "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": 35,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:50Z",
      "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": 1398.6125264834243,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 27.370645611635616,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 6
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "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": 24,
      "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": "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": 16,
      "max_score": null,
      "measured_at": "2026-08-23T12:24:56Z",
      "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": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.7350302187187,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.9119831179808,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "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": 37,
      "draws": 41,
      "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": 33,
      "max_score": null,
      "measured_at": "2026-08-22T04:21:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1395.4317548321806,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.729763986537332,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 152,
      "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": 59,
      "draws": 94,
      "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": 46,
      "max_score": null,
      "measured_at": "2026-08-22T06:20:20Z",
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1380.6694525948496,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.24251380391939,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:deepseek-deepseek-v4-flash:865c6d4e9c2ee4b8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "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": "deepseek/deepseek-v4-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": 26,
      "max_score": null,
      "measured_at": "2026-08-03T14:54:22Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1363.997401760583,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 21.587325373198095,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2,
      "attempted_matches": 285,
      "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": 106,
      "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": "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": 90,
      "max_score": null,
      "measured_at": "2026-08-23T06:52:50Z",
      "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": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1336.8963911626097,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.174525876824212,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.8522727272727293,
      "unilateral_faults": 23,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:openai-gpt-oss-120b:7785ef5b91a441ff",
      "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": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 71,
      "max_score": null,
      "measured_at": "2026-08-23T02:43:04Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1210.9553390354572,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-4:00c166645bf94fd4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:53:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 2048.0082481553145,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "XHigh (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 93.10453249742434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 86
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-fable-5:9765333017ba86fe",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-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": 16,
      "max_score": null,
      "measured_at": "2026-08-05T00:52:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 2023.8636251018338,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 91.20233840190105,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 84
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "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": 44,
      "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": 1,
      "max_score": null,
      "measured_at": "2026-08-22T08:04:25Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1994.8915096393325,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 88.69372140533535,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 93
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 238,
      "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": 119,
      "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": 24,
      "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": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1976.4988138269168,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 87.54201134418061,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.8947351529780132,
      "unilateral_faults": 0,
      "wins": 214
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 140,
      "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": 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-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": 22,
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1976.177267738965,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 86.6055678570907,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 118
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 226,
      "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": 113,
      "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": 28,
      "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": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1925.6591942822074,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 83.24150998152905,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.0806419155977727,
      "unilateral_faults": 0,
      "wins": 198
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "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": 45,
      "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": 21,
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1927.4799055461476,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 83.16542149104123,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 77
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 288,
      "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": 111,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 44,
      "max_score": null,
      "measured_at": "2026-08-20T05:43:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 288,
      "rating_method": "sequential_elo",
      "raw_elo": 1918.3075744153398,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 82.98344935650789,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 244
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 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",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-20T05:43:22Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1843.4523646471466,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 76.15353884909591,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 79
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:deepseek-deepseek-v4-pro:d03a9ec0db9a8b52",
      "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": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:40:18Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1818.7116137409091,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 74.1333084252556,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "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": 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-5.6-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": 17,
      "max_score": null,
      "measured_at": "2026-08-22T11:11:03Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1809.7744136870645,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 73.32160777460308,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-4:c42a41ea59ccc1f7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T03:33:35Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1797.5895875968265,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "None (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 72.27333144424207,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 142,
      "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": 56,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-08-22T10:31:06Z",
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1780.9418496208198,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 71.55758103790589,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 101
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 324,
      "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": 132,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 82,
      "max_score": null,
      "measured_at": "2026-08-23T02:44:09Z",
      "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": 324,
      "rating_method": "sequential_elo",
      "raw_elo": 1770.0664811162064,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 70.83047446085692,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-6-sol:683e7f269aa1d12e",
      "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": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:40:34Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1744.4095445478265,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "XHigh (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 67.89371257833555,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "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": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": "2026-08-05T04:43:10Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1717.6614023179375,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 65.742104336769,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 57,
      "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": 60,
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1685.2701621628198,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 63.41974151718129,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 102,
      "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": 45,
      "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": 47,
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1681.8135849530192,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 62.830767356755665,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-fable-5:99e7b840e9269907",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:01:05Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1679.6354629058385,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 62.71165398791373,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-6-terra:75cc7f062ffaf091",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:40:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1679.100259521219,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 62.53998912556835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-6-sol:db6839ea2087dc79",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T13:20:28Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1676.2772256568912,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 62.30556454623592,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 17,
      "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": 9,
      "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": 0,
      "max_score": null,
      "measured_at": "2026-08-22T14:19:11Z",
      "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": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1725.7042357575813,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 61.919231042616644,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 74.10113019775793,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-6-sol:7aebae84d73affb6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:32:52Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1665.4347956065355,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "None (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 61.405209741565095,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "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": 58,
      "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": 46,
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1660.642134309636,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 61.274740553352146,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "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": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 23,
      "max_score": null,
      "measured_at": "2026-08-15T00:19:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1649.8907644291016,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 59.931879001613865,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 185,
      "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": 77,
      "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": 65,
      "max_score": null,
      "measured_at": "2026-08-20T13:06:17Z",
      "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": 185,
      "rating_method": "sequential_elo",
      "raw_elo": 1633.2331677471427,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 59.63400603920557,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 120
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "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": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "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": 34,
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1643.2983032623679,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 59.344201371796736,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-6-luna:f9f63ab67ac1da8b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:40:50Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1629.976691086905,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "XHigh (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 58.61758837696586,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 46,
      "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": 48,
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1628.3276946126373,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 58.289597890358415,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 58,
      "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": 64,
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1607.3794802947366,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 56.95170350971318,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-6-terra:08cc40e91e1568bf",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:41:58Z",
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1609.1466507381233,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 56.91665552510462,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "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": 51,
      "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": 52,
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1607.1651624106053,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 56.63196638824444,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-6-luna:89e8232b6c428839",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:51:44Z",
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1602.8775455457373,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 56.477972228182814,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "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": 53,
      "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": 51,
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1601.2213719654865,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 56.229748233144726,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 57
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "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": 81,
      "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": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1597.9453407659207,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 55.5572678099564,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.16912059827689,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-sonnet-5:e2e304f6cedf7237",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:01:15Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1590.3103541790922,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 55.263664052390155,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "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": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 33,
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1593.0579629263639,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 55.212486240190024,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 57,
      "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": 58,
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1583.880968834933,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 55.00038838965367,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2,
      "attempted_matches": 196,
      "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": 98,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 71,
      "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": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1586.099222433189,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.815141934474596,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.532690756236184,
      "unilateral_faults": 0,
      "wins": 125
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "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": 53,
      "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": 40,
      "max_score": null,
      "measured_at": "2026-08-05T02:32:47Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1584.2090805580165,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.787452361508244,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-sonnet-5:906c16e3480819c2",
      "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": "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:16:36Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1584.3884545773712,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (historical request variant 3)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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-variant-3",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh (historical request variant 3)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-3",
        "reasoning_bucket_label": "XHigh (historical request variant 3)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-3"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-3",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.74058980227671,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "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": 44,
      "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": 35,
      "max_score": null,
      "measured_at": "2026-08-23T07:22:40Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1585.7142254237854,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.71566186567154,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 58,
      "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": 50,
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1576.1336146218378,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.357048515026754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 200,
      "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": 75,
      "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": 91,
      "max_score": null,
      "measured_at": "2026-08-20T05:12:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1557.6899839620967,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 53.45354337379487,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-6-terra:0983009cb1ffeee4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:20:58Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1567.3066590038927,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 53.15064951506388,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 32,
      "max_score": null,
      "measured_at": "2026-08-15T02:19:58Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1567.0954010065689,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "None (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 53.09546252248944,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 43,
      "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": 42,
      "max_score": null,
      "measured_at": "2026-08-20T12:15:34Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.788333723547,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 53.02456786594432,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "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": 42,
      "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": 42,
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1563.1378187943271,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.64602705866004,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemini-3-5-flash:5712a3e29dc27925",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-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": 54,
      "max_score": null,
      "measured_at": "2026-08-05T04:42:51Z",
      "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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1553.2266000489765,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.301082285856566,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 176,
      "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": 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": "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": 70,
      "max_score": null,
      "measured_at": "2026-08-20T12:14:57Z",
      "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": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1544.3586605576277,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.19271965091757,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 94,
      "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": 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": "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": 41,
      "max_score": null,
      "measured_at": "2026-08-23T02:44:09Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1554.8886887946508,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.15591097203426,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemini-3-5-flash:2637a22cd82f12e9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-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": 55,
      "max_score": null,
      "measured_at": "2026-08-03T10:18:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.7470805088597,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.08084603218233,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 40,
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1551.1627362890197,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 51.810059046408426,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:deepseek-deepseek-v4-flash:1ebaee0e9d08b232",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "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_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:16:36Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1549.0224155741603,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 51.803795837193945,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 59,
      "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": 63,
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1544.3386733865298,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 51.71679831534971,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 59,
      "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": 56,
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.859169314774,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 51.154684162643335,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 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-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": 65,
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.317407962045,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 51.00200589427959,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2,
      "attempted_matches": 208,
      "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": 103,
      "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": 96,
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.204965591142,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.75472568681504,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.286300544311842,
      "unilateral_faults": 0,
      "wins": 112
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 634,
      "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": 232,
      "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": 292,
      "max_score": null,
      "measured_at": "2026-08-23T13:45:04Z",
      "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": 634,
      "rating_method": "sequential_elo",
      "raw_elo": 1525.5655874239144,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.49609918819178,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 342
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "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": 11,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:47Z",
      "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": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1577.631160970109,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.2040113856351,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 200,
      "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": 67,
      "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": 86,
      "max_score": null,
      "measured_at": "2026-08-20T05:43:17Z",
      "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": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.738619126404,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 49.55470457849347,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 94,
      "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": 45,
      "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": 39,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:47Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.3810009155313,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 49.4564743296236,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "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": 53,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 53,
      "max_score": null,
      "measured_at": "2026-08-05T03:40:38Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1515.586736592979,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 49.08905663197634,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 53
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 341,
      "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": 133,
      "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": 148,
      "max_score": null,
      "measured_at": "2026-08-22T23:45:14Z",
      "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": 341,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.2181493329292,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 48.89848482079757,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 193
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 166,
      "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": 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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T03:35:07Z",
      "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": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.119904446422,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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",
          "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 48.88616759311684,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 84
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "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": 24,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-08-23T14:10:47Z",
      "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": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1571.444849455973,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 48.8825630594869,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 56,
      "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": 50,
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.8097339730377,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 48.39087874034282,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 36,
      "max_score": null,
      "measured_at": "2026-08-22T11:11:03Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.1321010535598,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "None (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 48.282193230929145,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:cohere-north-mini-code:959513c67c4e5ee3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "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": 56,
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.9170144593968,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 47.666905146048265,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.157312871896224,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 58,
      "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": 66,
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.530653934251,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 47.2576469157077,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 22,
      "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": 11,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-08-22T11:34:23Z",
      "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": 22,
      "rating_method": "sequential_elo",
      "raw_elo": 1528.9563415565945,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.48436747017905,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 60.5072070285374,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 161,
      "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": 65,
      "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": 85,
      "max_score": null,
      "measured_at": "2026-08-22T23:41:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 161,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.9702034985373,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.31767802468079,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 92,
      "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": 44,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-08-23T07:22:40Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.5916885129375,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.03288300374409,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "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": 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": "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": 54,
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.341736666781,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.76839619365652,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "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": 58,
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.3464738181478,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.19689169842294,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 93,
      "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": 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-5.6-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": 49,
      "max_score": null,
      "measured_at": "2026-08-22T11:01:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 93,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.8329908962558,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.15785126150731,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.821062312939668,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-4:ef3925c3f5fdbb2d",
      "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-5.4",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:25:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.6644809842144,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.802830877695115,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 106,
      "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": 53,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 53,
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.6103813613147,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.77294290610812,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:openai-gpt-oss-120b:f9a4cf175428ff96",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:10:14Z",
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.517503684909,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.324242271963605,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 130,
      "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": 63,
      "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": 67,
      "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": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.9669001608218,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.69988545387929,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 17,
      "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": 9,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-20T12:56:07Z",
      "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": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.5327853795927,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.47012582547535,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 74.10113019775793,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "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": 24,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-08-23T14:12:11Z",
      "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": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.807691416014,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.09989722408759,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "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": 49,
      "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": 46,
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.8486850159818,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.08775105458573,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 52
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 210,
      "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": 102,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 122,
      "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": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.4480042293753,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 42.912176221849236,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.89396709107023,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "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": 52,
      "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": 52,
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.1003871142666,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.604671181441674,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 56
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 342,
      "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": 125,
      "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": 190,
      "max_score": null,
      "measured_at": "2026-08-22T11:34:23Z",
      "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": 342,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.4395331894639,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.53426134564661,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-sonnet-5:3d227889fd8fad8f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "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": "2026-08-05T03:40:38Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.5046512373144,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking 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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Thinking disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.35208234845052,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:deepseek-deepseek-v4-flash:865c6d4e9c2ee4b8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:55:59Z",
      "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": 1404.752960189545,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.99912971379366,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:deepseek-deepseek-v4-pro:a4cf9c7798e0d7dc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T11:37:30Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1393.141045545112,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.79395147095302,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 57,
      "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": 73,
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1384.689357216663,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.33304920861673,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "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": 49,
      "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": 55,
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1386.8051899721886,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.26782236702627,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 43
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "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": 24,
      "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": 34,
      "max_score": null,
      "measured_at": "2026-08-23T14:12:11Z",
      "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": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.7474591280127,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.866899596586855,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 45,
      "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": 63,
      "max_score": null,
      "measured_at": "2026-08-22T14:19:11Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1357.2618578161205,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking 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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Thinking disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.70854059047516,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:mistralai-mistral-medium-3-5:6deb1b60bb205df7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "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": 52,
      "max_score": null,
      "measured_at": "2026-08-03T11:38:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1351.468176625996,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.33343869093166,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 46
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 170,
      "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": 85,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 99,
      "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": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1335.5227035784274,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 33.76570621824515,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.16912059827689,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "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": 63,
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1329.3883779909766,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 33.59671726886273,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 41
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 375,
      "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": 138,
      "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": 252,
      "max_score": null,
      "measured_at": "2026-08-22T14:35:15Z",
      "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": 375,
      "rating_method": "sequential_elo",
      "raw_elo": 1299.0500309172046,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.896275052743633,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 154,
      "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": 56,
      "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": 99,
      "max_score": null,
      "measured_at": "2026-08-22T10:50:26Z",
      "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": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1299.4636047831602,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.650235307750318,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 16,
      "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": 8,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-08-20T12:25:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1363.5335221414252,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.61761768988316,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 214,
      "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": 107,
      "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": 142,
      "max_score": null,
      "measured_at": "2026-08-05T03:40:47Z",
      "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": 1298.8487134830848,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.105118393569768,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.376451717525809,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "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": 53,
      "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": 71,
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1293.3384425319216,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.691959004825147,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "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": 52,
      "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": 74,
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1281.5487586993647,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.654555612064655,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 32
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 158,
      "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": 79,
      "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": 93,
      "max_score": null,
      "measured_at": "2026-07-31T03:33:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1284.9171506996952,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.431499631947965,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.154975300928378,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 59,
      "max_score": null,
      "measured_at": "2026-08-22T10:50:31Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1273.8587217985935,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "None (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 28.782748688729765,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1,
      "attempted_matches": 94,
      "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": 47,
      "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": 66,
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1258.1950094624974,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 27.518483895121314,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 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",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:51:41Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1241.8551704733636,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.598584601571144,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:mistralai-mistral-medium-3-5:54288de170df8ebb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "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": 65,
      "max_score": null,
      "measured_at": "2026-08-05T01:39:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1231.6665190864155,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 25.241466318726623,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "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": 7,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-08-20T12:05:25Z",
      "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": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1275.2637241074317,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 24.72348845861986,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 70.95786693528086,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 300,
      "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": 105,
      "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": 222,
      "max_score": null,
      "measured_at": "2026-08-22T23:45:14Z",
      "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": 300,
      "rating_method": "sequential_elo",
      "raw_elo": 1209.9376686322128,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 24.21600641424555,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 98,
      "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": 49,
      "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": 70,
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1196.77816581129,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 22.487988563537684,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 28
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 178,
      "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": 89,
      "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": 136,
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1169.1766725591847,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 20.032859834975213,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.957067918206963,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "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": 43,
      "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": 70,
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1165.8540579796686,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.73749709047673,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 18
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 320,
      "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": 112,
      "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": 250,
      "max_score": null,
      "measured_at": "2026-08-22T23:41:42Z",
      "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": 1139.8966108091176,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 18.48372816664021,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 94,
      "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": 47,
      "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": 67,
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1136.0733751755404,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 17.377509992236185,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "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": 47,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-08-05T04:55:59Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1135.4295707705774,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 17.324048509285905,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 28
    },
    {
      "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:f12274812b7e4c60",
      "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": "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": 59,
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1136.308456520139,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 17.067829071463514,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2,
      "attempted_matches": 326,
      "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": 123,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 259,
      "max_score": null,
      "measured_at": "2026-08-22T12:02:21Z",
      "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": 326,
      "rating_method": "sequential_elo",
      "raw_elo": 1115.6686528221212,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 16.497222114125087,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 182,
      "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": 89,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 130,
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1103.7825250791311,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 14.601235431191899,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.9766057392055,
      "unilateral_faults": 4,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 189,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:openai-gpt-oss-120b:7785ef5b91a441ff",
      "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": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "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": 153,
      "max_score": null,
      "measured_at": "2026-08-23T13:45:04Z",
      "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": 189,
      "rating_method": "sequential_elo",
      "raw_elo": 1087.1904502695809,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 14.31642168470547,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 326,
      "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": 118,
      "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": 277,
      "max_score": null,
      "measured_at": "2026-08-22T19:33:48Z",
      "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": 324,
      "rating_method": "sequential_elo",
      "raw_elo": 1028.8157077908918,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 9.276903456466506,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-6-luna:fd12531a88a47fab",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T23:25:01Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 997.5922414110602,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "None (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 5.724804936416754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 2,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "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": 52,
      "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": 103,
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 924.4368254590598,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 43,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-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": 1,
      "max_score": null,
      "measured_at": "2026-08-21T05:32:10Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1996.2299624147333,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 92.42283491539342,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 83
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 52,
      "draws": 11,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-08-03T14:04:35Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1978.901816863329,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 91.17466067700593,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 88
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 314,
      "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": 124,
      "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": "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": 46,
      "max_score": null,
      "measured_at": "2026-08-23T03:04:24Z",
      "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": 314,
      "rating_method": "sequential_elo",
      "raw_elo": 1969.472492857064,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 90.98102138726986,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 254
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 308,
      "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": 121,
      "draws": 21,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 21,
      "max_score": null,
      "measured_at": "2026-08-23T09:38:44Z",
      "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": 308,
      "rating_method": "sequential_elo",
      "raw_elo": 1956.8985581879415,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 89.86912515095916,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 266
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-4:00c166645bf94fd4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "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-5.4",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T23:53:06Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1963.0028481780307,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "XHigh (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 89.42348069013059,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 43,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 6,
      "max_score": null,
      "measured_at": "2026-08-20T17:51:34Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1948.9952096118298,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 88.45182081930464,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 87
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-4:ef3925c3f5fdbb2d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "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-5.4",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T13:20:41Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1911.8869424079114,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 84.95793522748247,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-fable-5:9765333017ba86fe",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 9,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:01:50Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1909.8483590250705,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 84.82657150590221,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "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": 41,
      "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-5.5",
        "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": 16,
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1909.8196476234893,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 84.82408848503748,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 42,
      "draws": 3,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-22T11:41:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1886.7419988126178,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 82.99329591592327,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemini-3-5-flash:2637a22cd82f12e9",
      "capped_draws": 0,
      "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": "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:25:28Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1877.810620435143,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 82.05588219794666,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 42,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-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": 9,
      "max_score": null,
      "measured_at": "2026-08-22T20:09:21Z",
      "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": 89,
      "rating_method": "sequential_elo",
      "raw_elo": 1876.2466265033572,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 82.02633954021168,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.954627669472988,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemini-3-5-flash:5712a3e29dc27925",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-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": 12,
      "max_score": null,
      "measured_at": "2026-08-03T12:16:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1868.3321704609657,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 81.27954496028467,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "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": 38,
      "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-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": 18,
      "max_score": null,
      "measured_at": "2026-08-04T23:53:43Z",
      "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": 1827.373724966149,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 77.69399608634865,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-6-sol:db6839ea2087dc79",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T09:48:51Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1817.2618046108626,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 76.98450629273803,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-fable-5:99e7b840e9269907",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "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-fable-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-08-03T10:57:46Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1815.5838157198623,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 76.8393903737067,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-6-sol:683e7f269aa1d12e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:37:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1810.9235349193502,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "XHigh (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 76.31472847571924,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 46,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1799.7073501929144,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 75.46636108950283,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-6-luna:f9f63ab67ac1da8b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "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-5.6-luna",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:04:23Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1790.7895280558996,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "XHigh (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 74.57349828912908,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 96,
      "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": 43,
      "draws": 4,
      "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": 18,
      "max_score": null,
      "measured_at": "2026-08-20T18:11:07Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1780.420554955911,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "None (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 73.87313912064397,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-6-terra:75cc7f062ffaf091",
      "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": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:37:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1762.4255362201798,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 72.24215339252389,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "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": 47,
      "draws": 5,
      "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": 31,
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1740.616275075024,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 70.50103787240695,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-4:c42a41ea59ccc1f7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "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-5.4",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T09:48:41Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1716.938756792082,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "None (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 68.14335365615862,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:openai-gpt-oss-120b:d658f92b65107751",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "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": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T11:32:58Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1712.237284828002,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 67.82204727657161,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-6-luna:89e8232b6c428839",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "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": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T06:37:01Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1693.5219286366255,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 66.55694526663,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 42,
      "draws": 9,
      "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": 31,
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1690.7719660077682,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 66.00620122264021,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 72,
      "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": 36,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 25,
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1689.1739025328532,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 65.44552694683463,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "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": 52,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1677.2246416402638,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 65.17750853680307,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 190,
      "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": 73,
      "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": "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": 74,
      "max_score": null,
      "measured_at": "2026-08-20T21:54:25Z",
      "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": 190,
      "rating_method": "sequential_elo",
      "raw_elo": 1661.6059928496998,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 64.6071323338313,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:deepseek-deepseek-v4-pro:a4cf9c7798e0d7dc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T11:04:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1670.4616001827212,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 64.1672924244156,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 93,
      "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": 43,
      "draws": 3,
      "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": 28,
      "max_score": null,
      "measured_at": "2026-08-22T11:41:43Z",
      "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": 93,
      "rating_method": "sequential_elo",
      "raw_elo": 1656.6269296223352,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "None (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 63.111604396432526,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.821062312939668,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 214,
      "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": 106,
      "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-5.4-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": 86,
      "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": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1634.145784366343,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 61.40570645858217,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.376451717525809,
      "unilateral_faults": 0,
      "wins": 122
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 184,
      "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": 68,
      "draws": 20,
      "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": 70,
      "max_score": null,
      "measured_at": "2026-08-20T21:14:21Z",
      "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": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1623.3658987890403,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 61.25978450989219,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-sonnet-5:906c16e3480819c2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:01:59Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1630.987339864078,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (historical request variant 3)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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-variant-3",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh (historical request variant 3)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-3",
        "reasoning_bucket_label": "XHigh (historical request variant 3)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-3"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-3",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 60.949848353843976,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2,
      "attempted_matches": 302,
      "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": 113,
      "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-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": 116,
      "max_score": null,
      "measured_at": "2026-08-23T03:04:24Z",
      "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": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1620.4034216639773,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 60.74100437018801,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 182
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "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": 47,
      "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": "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": 37,
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1625.0173972189637,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 60.46921496514469,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 92,
      "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": 43,
      "draws": 3,
      "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": 32,
      "max_score": null,
      "measured_at": "2026-08-22T22:29:24Z",
      "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": 91,
      "rating_method": "sequential_elo",
      "raw_elo": 1617.2068115368675,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 59.663897931635695,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.378603514268699,
      "unilateral_faults": 1,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 178,
      "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": 64,
      "draws": 17,
      "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": 71,
      "max_score": null,
      "measured_at": "2026-08-20T18:12:10Z",
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1601.6726322378718,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 59.34143229501704,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 156,
      "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": 54,
      "draws": 8,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-08-22T13:31:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1594.5323147640372,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 58.54870417164183,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 106,
      "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": 52,
      "draws": 11,
      "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": 43,
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1597.6476744413671,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 58.234720321902785,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 52
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 150,
      "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": 75,
      "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": "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": 65,
      "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": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1599.5647166016763,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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",
          "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 57.774334362784295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.637484322183244,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "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": 52,
      "draws": 12,
      "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": 42,
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1579.5531911998273,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 56.73068128436687,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 51,
      "draws": 7,
      "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": 42,
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1580.3019624316037,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 56.70292816921177,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-sonnet-5:3d227889fd8fad8f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "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-sonnet-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": 39,
      "max_score": null,
      "measured_at": "2026-08-03T13:58:14Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1575.5939478505748,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking 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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Thinking disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 55.96294337993718,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "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": 36,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 30,
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1577.339884678403,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 55.77389183234963,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 108,
      "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": 54,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:53:50Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.2793243998406,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.94736966606298,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 45,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-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": 30,
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.4794101376715,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.6517518521781,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 46,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 35,
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1555.174459690298,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.318655446755876,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 16,
      "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": 9,
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-22T19:42:16Z",
      "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": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1608.3676756467582,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.116030920939295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 182,
      "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": 65,
      "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": "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": 82,
      "max_score": null,
      "measured_at": "2026-08-23T08:13:25Z",
      "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": 182,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.3129835742382,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.06333802227879,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 20,
      "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": 10,
      "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": "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": 6,
      "max_score": null,
      "measured_at": "2026-08-22T11:01:36Z",
      "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": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1596.932346317202,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 53.968299220992186,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 11,
      "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": 70,
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.3131958934082,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.94752904365944,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 163,
      "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": 60,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "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": 68,
      "max_score": null,
      "measured_at": "2026-08-22T18:02:35Z",
      "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": 163,
      "rating_method": "sequential_elo",
      "raw_elo": 1506.1558845685156,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.965291500953946,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 164,
      "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": 60,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 68,
      "max_score": null,
      "measured_at": "2026-08-20T21:54:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.431236228724,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.91082045936282,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 3,
      "attempted_matches": 42,
      "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": 21,
      "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": "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": 8,
      "max_score": null,
      "measured_at": "2026-08-23T12:25:25Z",
      "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": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1577.0114222032025,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.86244134919709,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 196,
      "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": 71,
      "draws": 16,
      "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": 82,
      "max_score": null,
      "measured_at": "2026-08-20T18:11:58Z",
      "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": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.9782452617544,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.754127680852754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-6-terra:08cc40e91e1568bf",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:57:28Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.2749957494511,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 49.922377861903456,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 48
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 196,
      "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": 96,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 86,
      "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": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.2372841051183,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 49.76392479065197,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.5095838835902065,
      "unilateral_faults": 0,
      "wins": 109
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 168,
      "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": 84,
      "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",
        "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": 80,
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.2933388996616,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 49.49311656057918,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.493878368367454,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 591,
      "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": 205,
      "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": "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": 286,
      "max_score": null,
      "measured_at": "2026-08-23T04:58:48Z",
      "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": 591,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.5307015706844,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 49.13258160734104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 288
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "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": 43,
      "draws": 4,
      "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": 45,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:37Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.6367483030979,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking 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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Thinking disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 49.03470790545843,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 60,
      "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": 73,
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.311575824817,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 47.27455398323267,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 15,
      "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": 9,
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-22T16:31:50Z",
      "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": 15,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.7378338885317,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.45237289235433,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 81.25,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 216,
      "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": 106,
      "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": "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": 108,
      "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": 216,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.432472937302,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.215404534608886,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.293407807185584,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 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": "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": 62,
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.9671489840152,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.169198045990534,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-sonnet-5:e2e304f6cedf7237",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "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-sonnet-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": 54,
      "max_score": null,
      "measured_at": "2026-08-05T02:42:19Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.2412427006718,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.08074790155403,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2,
      "attempted_matches": 294,
      "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": 106,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 152,
      "max_score": null,
      "measured_at": "2026-08-23T00:33:30Z",
      "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": 294,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.0497650366196,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.75966543731385,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 129
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06: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": 48,
      "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": 44,
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.511289483019,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.871714707416494,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 94,
      "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": 44,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-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": 58,
      "max_score": null,
      "measured_at": "2026-08-22T17:46:09Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.842052186386,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.517611811465784,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 3,
      "attempted_matches": 42,
      "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": 21,
      "draws": 1,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-08-23T14:12:18Z",
      "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": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.8317645204697,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.15000174191575,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 57,
      "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": 73,
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.0192370849595,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.0367051388074,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "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": 51,
      "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": 45,
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.6211054795062,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 42.94726409759388,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "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": 52,
      "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": 64,
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1412.0094597124114,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 42.18034696924738,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "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": 66,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 82,
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1399.0006395624505,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.39995376105174,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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:GB2-06:publication-row.v1:mixed:deepseek-deepseek-v4-pro:d03a9ec0db9a8b52",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T23:08:34Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1399.9603695080434,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.31141247367678,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 91,
      "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": 46,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 59,
      "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": 91,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.9558533954528,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.27021537575938,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.378603514268699,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "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": 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": "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": 36,
      "max_score": null,
      "measured_at": "2026-07-31T02:02:44Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1381.2364236832755,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.0195992003968,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-6-terra:0983009cb1ffeee4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:04:35Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1373.9806181391325,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.82721709336295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-6-sol:7aebae84d73affb6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 3,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T13:58:14Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1364.2292853844367,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "None (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.95031944195105,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 59,
      "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": 79,
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1342.8613766220567,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.399691312701414,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 59,
      "draws": 5,
      "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": 77,
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1340.4538958273813,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.242213374439,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 121,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:openai-gpt-oss-120b:f9a4cf175428ff96",
      "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": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T20:06:27Z",
      "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": 121,
      "rating_method": "sequential_elo",
      "raw_elo": 1340.0030877685297,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.16541568514887,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 42
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 28,
      "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": 14,
      "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": "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": 22,
      "max_score": null,
      "measured_at": "2026-08-23T12:15:59Z",
      "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": 28,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.7352199144916,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.79067812355425,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 85.34944487358055,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "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": 58,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 76,
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1333.1575713568993,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.53416954938754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 98,
      "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": 47,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 46,
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1335.615860264783,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.44117680027425,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 19,
      "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": 9,
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-23T04:48:33Z",
      "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": 19,
      "rating_method": "sequential_elo",
      "raw_elo": 1377.382181449011,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.79473339617072,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 68.05339887498948,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 43,
      "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-5.6-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": 53,
      "max_score": null,
      "measured_at": "2026-08-23T00:03:03Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1325.565033749482,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.46156161117417,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 21,
      "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": 10,
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-23T00:33:30Z",
      "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": 21,
      "rating_method": "sequential_elo",
      "raw_elo": 1368.9037533119765,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.421477251042134,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 62.850358177805205,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:mistralai-mistral-medium-3-5:6deb1b60bb205df7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:42:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1323.4952044044514,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.24335399238109,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "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": 48,
      "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": 56,
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1318.8645561550443,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.02708466427257,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "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": 54,
      "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": 58,
      "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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1315.7125886364151,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 33.94239152620984,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "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": 49,
      "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": 59,
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1313.9232512674864,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 33.633332893697606,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 42,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-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": 64,
      "max_score": null,
      "measured_at": "2026-08-23T08:13:25Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1282.520215691405,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.738957507215925,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 23
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 346,
      "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": 131,
      "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": "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": 227,
      "max_score": null,
      "measured_at": "2026-08-22T19:42:16Z",
      "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": 346,
      "rating_method": "sequential_elo",
      "raw_elo": 1266.7108166706953,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.33372549288365,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 112,
      "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": 56,
      "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": 78,
      "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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1267.48183370103,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.77129697036285,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:deepseek-deepseek-v4-flash:1ebaee0e9d08b232",
      "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": "xhigh",
        "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_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:53:03Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1269.9135910657938,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.52707950589016,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 95,
      "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": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 66,
      "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": 95,
      "rating_method": "sequential_elo",
      "raw_elo": 1265.0077154404437,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.280934011909366,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.281036307982882,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 329,
      "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": 118,
      "draws": 35,
      "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": 212,
      "max_score": null,
      "measured_at": "2026-08-23T09:38:44Z",
      "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": 329,
      "rating_method": "sequential_elo",
      "raw_elo": 1254.9959580997784,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.256284231675217,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 16,
      "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": 10,
      "draws": 2,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-08-22T23:34:51Z",
      "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": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1320.8161587044958,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.24798627908666,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:cohere-north-mini-code:959513c67c4e5ee3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 35,
      "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": 79,
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1268.3538600217935,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 28.469827580005035,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.187341079842824,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:mistralai-mistral-medium-3-5:54288de170df8ebb",
      "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": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "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": 62,
      "max_score": null,
      "measured_at": "2026-08-05T02:35:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1253.7221512485582,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 28.20923732650551,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "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": 43,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-08-20T21:45:35Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1250.7317045501534,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 28.027781786573513,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "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": 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": "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": 49,
      "max_score": null,
      "measured_at": "2026-07-31T02:45:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1244.3425660567527,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 27.180737771836384,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2,
      "attempted_matches": 160,
      "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": 80,
      "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": "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": 101,
      "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": 160,
      "rating_method": "sequential_elo",
      "raw_elo": 1244.2632602994895,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 27.173879247378046,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:inclusionai-ling-3-0-flash:20c76d20ae9b2569",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 26,
      "draws": 2,
      "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": 137,
      "max_score": null,
      "measured_at": "2026-08-22T10:20:46Z",
      "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": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1240.7179893577259,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.835290028835875,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.465140987172258,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 43,
      "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": 65,
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1236.8815002319625,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.752823304656847,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 99,
      "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": 48,
      "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": 71,
      "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": 99,
      "rating_method": "sequential_elo",
      "raw_elo": 1234.4468531079099,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.709300896929104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.25,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "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": 47,
      "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": 63,
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1225.4277449994963,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 25.9118827156635,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "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": 52,
      "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": 58,
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1210.0954507274137,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 24.749232472982165,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 45,
      "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": 67,
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1204.3990254582595,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 23.982876833913124,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "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": 52,
      "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": "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": 76,
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1195.0146527344775,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 23.41419124049507,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 44,
      "draws": 3,
      "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": 74,
      "max_score": null,
      "measured_at": "2026-08-22T23:34:51Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1192.954172313164,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "None (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 22.993102472928516,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 171,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:openai-gpt-oss-120b:7785ef5b91a441ff",
      "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": "openai/gpt-oss-120b",
        "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": 121,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:37Z",
      "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": 171,
      "rating_method": "sequential_elo",
      "raw_elo": 1181.1910568908093,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 22.92523467244584,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 176,
      "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": 66,
      "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": "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": 125,
      "max_score": null,
      "measured_at": "2026-08-21T05:34:21Z",
      "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": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1156.182973847154,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 20.800006608149722,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 168,
      "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": 62,
      "draws": 26,
      "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": 115,
      "max_score": null,
      "measured_at": "2026-08-20T21:45:46Z",
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1154.7845709020912,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 20.618239276105058,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 316,
      "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": 120,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-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": 260,
      "max_score": null,
      "measured_at": "2026-08-23T00:03:03Z",
      "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": 316,
      "rating_method": "sequential_elo",
      "raw_elo": 1145.0239194216756,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.691715205934457,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:deepseek-deepseek-v4-flash:865c6d4e9c2ee4b8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "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-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": 70,
      "max_score": null,
      "measured_at": "2026-08-05T03:19:58Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1123.1640710825773,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 16.918306920549412,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 258,
      "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": 100,
      "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": 192,
      "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": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1103.1532899366941,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 15.779988068257042,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.13627265814059708,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-6-luna:fd12531a88a47fab",
      "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-5.6-luna",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:51:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 978.4527453835951,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "None (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 4.4033748279235585,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "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": 37,
      "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": "2026-08-05T04:22:40Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 2071.119577926703,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "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": 46,
      "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": 6,
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1985.8838134621776,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 92.32704029193545,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 92
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 42,
      "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": 1,
      "max_score": null,
      "measured_at": "2026-08-23T08:55:50Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1984.8748904849485,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 92.06929067805841,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-4:00c166645bf94fd4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:13:26Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1954.8997479714724,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "XHigh (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 89.41112100908529,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 87
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 196,
      "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": 98,
      "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": 33,
      "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": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1921.5873524622293,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 86.2614975844883,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.695604130687789,
      "unilateral_faults": 0,
      "wins": 163
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 42,
      "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": 7,
      "max_score": null,
      "measured_at": "2026-08-19T21:21:29Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1906.2070120045769,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 84.78982880227399,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "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": 50,
      "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": 22,
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1856.1879837603456,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 80.15897505759567,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 43,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-08-19T21:56:52Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1850.56158757978,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 79.47168985931388,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "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": 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-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": 21,
      "max_score": null,
      "measured_at": "2026-08-05T04:35:38Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1824.9248359828734,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 77.1003159963057,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-6-luna:f9f63ab67ac1da8b",
      "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": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:42:46Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1821.0704465715448,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "XHigh (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 76.7776022306421,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-6-terra:75cc7f062ffaf091",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:18:27Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1780.4659593446845,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 72.91627837470821,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "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": 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": "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": 21,
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1780.9950468049765,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 72.79240290081826,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:deepseek-deepseek-v4-flash:1ebaee0e9d08b232",
      "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": "xhigh",
        "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_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:42:46Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1770.709939839599,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 72.03816050961174,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 146,
      "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": 57,
      "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": 33,
      "max_score": null,
      "measured_at": "2026-08-22T14:34:56Z",
      "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": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1761.1992839087297,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 71.8604564523625,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 113
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-fable-5:99e7b840e9269907",
      "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": "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:28:37Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1769.0766033480754,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 71.7604520313932,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 20,
      "max_score": null,
      "measured_at": "2026-08-22T06:40:22Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1757.382313941039,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 70.65989910390739,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 70
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 298,
      "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": 117,
      "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": 97,
      "max_score": null,
      "measured_at": "2026-08-22T15:50:15Z",
      "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": 298,
      "rating_method": "sequential_elo",
      "raw_elo": 1734.4124904712762,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 69.37028762269674,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 94,
      "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": 46,
      "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": 32,
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1740.3549601868879,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 69.14142074882011,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-fable-5:9765333017ba86fe",
      "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": "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:43:03Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1735.946996477361,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 68.72658602086715,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 42,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-08-22T23:00:29Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1731.131155491913,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 68.23205766874142,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 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": "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": 22,
      "max_score": null,
      "measured_at": "2026-08-19T21:22:21Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1713.3713882243446,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 66.56068088153548,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 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": "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": 32,
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1703.2609653449783,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 65.56652347725021,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "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": 8,
      "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": 0,
      "max_score": null,
      "measured_at": "2026-08-22T06:40:22Z",
      "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": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1746.3008626110957,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 65.34857672458816,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "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": 51,
      "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": 34,
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1681.4932621274972,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 63.75494931550506,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 166,
      "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": 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": "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": 62,
      "max_score": null,
      "measured_at": "2026-08-23T02:23:52Z",
      "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": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1657.3711692973993,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 62.28100802900767,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemini-3-5-flash:2637a22cd82f12e9",
      "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": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-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": 42,
      "max_score": null,
      "measured_at": "2026-08-04T22:51:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1663.7552103873281,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 61.804532842080334,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "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": 56,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "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": 47,
      "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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1656.3784608491428,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 61.55931257885285,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-6-sol:683e7f269aa1d12e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:43:23Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1649.6684403120166,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "XHigh (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 60.68571517101774,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-6-sol:db6839ea2087dc79",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T22:40:32Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1648.549683693386,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 60.5804286650213,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 29,
      "max_score": null,
      "measured_at": "2026-08-03T14:14:11Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1648.1717121399788,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 60.50605278337446,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-4:ef3925c3f5fdbb2d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:34:37Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1644.7476027576552,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 60.29680478151199,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-6-sol:7aebae84d73affb6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:35:22Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1643.747048162753,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "None (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 60.00831428515665,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "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": 53,
      "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": 42,
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1636.9247706055485,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 59.630586714276724,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "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": 50,
      "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": 40,
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1636.8698724185067,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 59.51888474627783,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 180,
      "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": 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": "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": 68,
      "max_score": null,
      "measured_at": "2026-08-19T21:33:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 180,
      "rating_method": "sequential_elo",
      "raw_elo": 1612.648077127973,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 58.18702905042954,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 96,
      "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": 47,
      "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": 43,
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.540591357989,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 57.24690808187588,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-sonnet-5:3d227889fd8fad8f",
      "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": "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": "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": 44,
      "max_score": null,
      "measured_at": "2026-08-03T14:14:11Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1604.343784837266,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking 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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Thinking disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 56.38139398455826,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 52
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "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": 70,
      "max_score": null,
      "measured_at": "2026-07-31T03:01:10Z",
      "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": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1606.386881654611,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 56.15647799029293,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 86
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:deepseek-deepseek-v4-pro:d03a9ec0db9a8b52",
      "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": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:16:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1598.2368673537846,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 55.8831215680576,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2,
      "attempted_matches": 286,
      "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": 129,
      "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": 120,
      "max_score": null,
      "measured_at": "2026-08-22T19:47:34Z",
      "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": 286,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.677153651903,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 53.4179924942283,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 196,
      "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": 74,
      "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": 102,
      "max_score": null,
      "measured_at": "2026-08-19T21:21:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1557.3437342280079,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 53.09835437853516,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 94
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 315,
      "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": 116,
      "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": 147,
      "max_score": null,
      "measured_at": "2026-08-23T02:42:49Z",
      "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": 311,
      "rating_method": "sequential_elo",
      "raw_elo": 1557.3822819538093,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.7743268035604,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 164
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "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": 53,
      "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": 48,
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1562.733366371016,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.68195407315516,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 166,
      "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": 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": "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": 80,
      "max_score": null,
      "measured_at": "2026-08-23T08:55:50Z",
      "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": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1543.6832616568183,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 51.58180645988167,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 96,
      "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": 48,
      "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": 39,
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1550.4563465439146,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 51.31003172352387,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemini-3-5-flash:5712a3e29dc27925",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-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": 53,
      "max_score": null,
      "measured_at": "2026-08-05T04:34:15Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1543.7114866663292,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.89179952279148,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 55
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 211,
      "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": 100,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 113,
      "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": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 1544.010143590685,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.79810134192654,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.759161709357059,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 93,
      "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": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 37,
      "max_score": null,
      "measured_at": "2026-08-22T19:47:34Z",
      "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": 93,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.286379381379,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "None (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.76297141256903,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.821062312939668,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "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": 47,
      "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": 37,
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.1060983283344,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.20183268472181,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 42,
      "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": 39,
      "max_score": null,
      "measured_at": "2026-08-22T23:00:29Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1538.9093254268835,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.09934354410103,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "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": 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": "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": 45,
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.730322602996,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.01827167679295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "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": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 34,
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.4625749629602,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 49.96560708699275,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-sonnet-5:e2e304f6cedf7237",
      "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-sonnet-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": 52,
      "max_score": null,
      "measured_at": "2026-08-05T01:39:22Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1528.418380946387,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 49.69122123778862,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 88,
      "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": 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-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": 48,
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1530.801634444942,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 49.29223370785008,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 152,
      "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": 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": "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": 83,
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.489111184017,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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",
          "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 47.92684620493954,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 162,
      "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": 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": "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": 74,
      "max_score": null,
      "measured_at": "2026-08-22T19:11:52Z",
      "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": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.6788239490022,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 47.781451793024814,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 170,
      "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": 61,
      "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": 77,
      "max_score": null,
      "measured_at": "2026-08-19T21:21:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.1314410426282,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 47.705624366124106,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 19,
      "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": 10,
      "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": 7,
      "max_score": null,
      "measured_at": "2026-08-23T02:23:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 19,
      "rating_method": "sequential_elo",
      "raw_elo": 1558.924963586655,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 47.51171651636437,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 68.05339887498948,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "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": 55,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 53,
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.7235320013426,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 47.25397426838036,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 63
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "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": 24,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-08-23T14:09:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1557.9397208469782,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.70643609553631,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "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": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "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": 40,
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.523954140653,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.066351390998115,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 19,
      "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": 9,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-22T15:50:02Z",
      "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": 19,
      "rating_method": "sequential_elo",
      "raw_elo": 1542.484591986778,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.96450843356181,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 68.05339887498948,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 56,
      "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": 58,
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.907737533893,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.82355270808264,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-6-luna:89e8232b6c428839",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:28:19Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.6145781538792,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.80193413103889,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 50
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 636,
      "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": 235,
      "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": 350,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 636,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.1447162410047,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.16236630356082,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 106,
      "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": 51,
      "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": 70,
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.7936186306395,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.84292897073299,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 36
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 315,
      "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": 116,
      "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": 162,
      "max_score": null,
      "measured_at": "2026-08-23T08:13:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 315,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.2642846072872,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.78344638910896,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-sonnet-5:906c16e3480819c2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-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": 57,
      "max_score": null,
      "measured_at": "2026-08-05T04:35:38Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.8322523216139,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (historical request variant 3)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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-variant-3",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh (historical request variant 3)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-3",
        "reasoning_bucket_label": "XHigh (historical request variant 3)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-3"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-3",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.40955503896284,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 59,
      "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": 62,
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.492796093447,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.90229671853825,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 112,
      "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": 56,
      "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": 54,
      "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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.820592135627,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.53174665691214,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "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": 55,
      "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": 53,
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.297529638152,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.356649989805135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "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": 54,
      "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": 59,
      "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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.1203052409805,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 42.524739590732,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "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": 55,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 57,
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.7149866418183,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 42.23519271244378,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:deepseek-deepseek-v4-pro:a4cf9c7798e0d7dc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:28:45Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.5598229415996,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.51464116371525,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 57
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:inclusionai-ling-3-0-flash:20c76d20ae9b2569",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 52,
      "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": 216,
      "max_score": null,
      "measured_at": "2026-08-19T21:22:25Z",
      "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": 380,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.0297347788198,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.40501950685979,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.465140987172258,
      "unilateral_faults": 0,
      "wins": 164
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 208,
      "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": 102,
      "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": 103,
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.1612694805494,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.853186603425755,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.071586885778516,
      "unilateral_faults": 0,
      "wins": 105
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:openai-gpt-oss-120b:d658f92b65107751",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:17:39Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.4652985743849,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.64119866533117,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 31
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "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": 24,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-08-23T12:27:10Z",
      "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": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.0816236736982,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.908636824800936,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:cohere-north-mini-code:959513c67c4e5ee3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 38,
      "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": 67,
      "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": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.0867753907792,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.36837714419139,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.45013723807159,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "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": 52,
      "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": 57,
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.849027987095,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.232485895385615,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 53
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "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": 24,
      "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": 28,
      "max_score": null,
      "measured_at": "2026-08-23T14:09:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.9786554793234,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.14606416585189,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-6-terra:0983009cb1ffeee4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:43:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.8298422557973,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.10393902588812,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 48
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 194,
      "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": 96,
      "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": 113,
      "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": 194,
      "rating_method": "sequential_elo",
      "raw_elo": 1403.2063184617587,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.47050308707877,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.7753885573785855,
      "unilateral_faults": 0,
      "wins": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "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": 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-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": 52,
      "max_score": null,
      "measured_at": "2026-08-19T21:31:53Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.3673294676476,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking 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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Thinking disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.39346503245966,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "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": 10,
      "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": 10,
      "max_score": null,
      "measured_at": "2026-08-22T06:50:33Z",
      "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": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.2408415859013,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.2529709637503,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 70.95786693528086,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 152,
      "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": 76,
      "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": 89,
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.3669338787731,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.187861256738046,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 178,
      "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": 68,
      "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": 109,
      "max_score": null,
      "measured_at": "2026-08-23T10:07:05Z",
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1378.7192000023038,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.156327157500364,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 98,
      "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": 43,
      "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": 60,
      "max_score": null,
      "measured_at": "2026-08-19T21:22:08Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1388.7768974869502,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.13313730855662,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-6-terra:08cc40e91e1568bf",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:18:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1379.3006758761821,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.51437146013137,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 55
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 322,
      "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": 126,
      "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": 191,
      "max_score": null,
      "measured_at": "2026-08-23T10:07:05Z",
      "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": 322,
      "rating_method": "sequential_elo",
      "raw_elo": 1372.8877030640774,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.46251830880079,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 131
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07: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": 42,
      "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": 62,
      "max_score": null,
      "measured_at": "2026-08-19T21:22:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1371.1011530410074,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "None (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.43086306273809,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "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": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 51,
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1367.2693290956158,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 33.90216158577543,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 20,
      "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": 11,
      "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": 14,
      "max_score": null,
      "measured_at": "2026-08-23T08:13:39Z",
      "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": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.8173258582663,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 33.305573503838346,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 101,
      "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": 50,
      "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": 66,
      "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": 101,
      "rating_method": "sequential_elo",
      "raw_elo": 1349.1712838775788,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.46189477313855,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.757377148833722,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "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": 42,
      "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": 58,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:30Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1339.6829441858488,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.305998996116344,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:deepseek-deepseek-v4-flash:865c6d4e9c2ee4b8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-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": 48,
      "max_score": null,
      "measured_at": "2026-08-03T00:20:40Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1337.0075281912582,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.9614054899469,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 43,
      "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": 61,
      "max_score": null,
      "measured_at": "2026-08-22T06:40:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1333.7149739611784,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.788444322361737,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 50,
      "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": 58,
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1324.660786450052,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.208838175428983,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 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": "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": 56,
      "max_score": null,
      "measured_at": "2026-08-05T04:09:52Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1320.0660988276552,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.776430806523866,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 160,
      "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": 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": "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": 112,
      "max_score": null,
      "measured_at": "2026-08-19T21:43:59Z",
      "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": 160,
      "rating_method": "sequential_elo",
      "raw_elo": 1302.1666353464232,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 28.7988247426727,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 100,
      "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": 50,
      "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": 62,
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1303.316043587365,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 28.128038323977535,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 178,
      "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": 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": "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": 121,
      "max_score": null,
      "measured_at": "2026-08-19T21:34:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1289.9508601455611,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 27.802313254046688,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 174,
      "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": 66,
      "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": 129,
      "max_score": null,
      "measured_at": "2026-08-22T06:50:33Z",
      "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": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1268.3605173911951,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 25.73846555139435,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 104,
      "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": 50,
      "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": 67,
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1276.1948853703204,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 25.647698335291103,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2,
      "attempted_matches": 194,
      "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": 89,
      "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": 130,
      "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": 190,
      "rating_method": "sequential_elo",
      "raw_elo": 1267.58485647528,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 24.665143039430337,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.33305067329769,
      "unilateral_faults": 4,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "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": 50,
      "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": 73,
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1249.6710367295523,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 23.186026838702013,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "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": 9,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-08-19T21:57:24Z",
      "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": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1304.7852176135736,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 22.881993246353847,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-4:c42a41ea59ccc1f7",
      "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-5.4",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:50:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1234.169410217102,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "None (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 21.376090075886736,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "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": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 59,
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1217.1234130773007,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.726281854437815,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 2,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:mistralai-mistral-medium-3-5:54288de170df8ebb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "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": 75,
      "max_score": null,
      "measured_at": "2026-08-05T04:22:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1213.7066599409454,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.618422210437004,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 156,
      "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": 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": "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": 117,
      "max_score": null,
      "measured_at": "2026-08-19T21:22:17Z",
      "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": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1158.879352478688,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 15.276461919221447,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 92,
      "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": 42,
      "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": 79,
      "max_score": null,
      "measured_at": "2026-08-23T02:42:49Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1147.5819193516577,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "None (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 13.314071820038254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "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": 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": "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": 62,
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1144.8702182648058,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 12.615617756799654,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "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": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "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": 59,
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1137.1745265340696,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 12.202269229827921,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 2,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 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": "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": 72,
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1120.4180547333053,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 10.757672736091521,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 168,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:openai-gpt-oss-120b:7785ef5b91a441ff",
      "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": "openai/gpt-oss-120b",
        "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": 142,
      "max_score": null,
      "measured_at": "2026-08-22T14:34:56Z",
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1108.1862556209687,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 10.614346337124728,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 87,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-6-luna:fd12531a88a47fab",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T23:25:47Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1096.9350151518765,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "None (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 8.415317281672394,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 1,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 156,
      "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": 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": "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": 139,
      "max_score": null,
      "measured_at": "2026-08-22T12:49:16Z",
      "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": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1082.0671538643896,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 8.04764389452622,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 90,
      "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": 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-5.4-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": 74,
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1090.5750082161858,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 7.8623797518037435,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 2,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "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": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 66,
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1053.14781558953,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 4.247286587507169,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 2,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "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": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 82,
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1011.5193889215823,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 0.5504962648416883,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 74,
      "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": 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/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": 70,
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1010.8187961005,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-fable-5:9765333017ba86fe",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "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-fable-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": 4,
      "max_score": null,
      "measured_at": "2026-08-05T04:44:21Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 2070.226734381098,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 97
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 178,
      "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": 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": "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": 8,
      "max_score": null,
      "measured_at": "2026-08-21T19:14:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 2021.4459228627536,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 96.03018425662745,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 178,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:x-ai-grok-4-5:5e133fd8ec34ed0c",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 68,
      "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": "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": 20,
      "max_score": null,
      "measured_at": "2026-08-22T17:44:01Z",
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1958.1843507591848,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 89.63424632680322,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 102,
      "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": 51,
      "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": 14,
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1930.9765683598841,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 85.92138340901016,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 87
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 206,
      "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": 103,
      "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": 28,
      "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": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1926.3153794356558,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 85.4691894172775,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.280733777820661,
      "unilateral_faults": 0,
      "wins": 178
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 174,
      "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": 72,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-08-22T18:02:47Z",
      "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": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1900.781455166142,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 83.79628828599199,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 176,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-4-5:e2ff6744eb1bb7c6",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "draws": 2,
      "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": 28,
      "max_score": null,
      "measured_at": "2026-08-21T15:41:46Z",
      "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": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1884.3566176372763,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 82.15300774815739,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08: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": 42,
      "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": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-23T02:42:42Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1884.7508193563601,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 80.99321920419641,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 42,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-08-23T02:42:42Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1859.6856893973443,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 78.50489070907093,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-fable-5:99e7b840e9269907",
      "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": "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:34:24Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1817.575241405041,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 74.2473959519865,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-sol:e7389fafab42de55",
      "capped_draws": 10,
      "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": "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": 13,
      "max_score": null,
      "measured_at": "2026-08-22T23:22:38Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1802.6772398837727,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "None (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 72.74116254930627,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 69
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 174,
      "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": 77,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:44:12Z",
      "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": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1797.9285674036369,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 72.14335911820079,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.552760371103872,
      "unilateral_faults": 0,
      "wins": 135
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-5:a77a9da79f1450e0",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "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": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:44:25Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1793.2236111969223,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 72.03227205758726,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "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": 47,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-08-05T04:22:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1792.3813910887834,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 71.86972819787296,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-sol:db6839ea2087dc79",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T08:03:23Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1776.669530520418,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 70.01850220623565,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "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": 45,
      "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": 25,
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1773.8635077665217,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 69.78217372191577,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-4-5:959db58a0f4d59b9",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 6,
      "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": 19,
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1770.4607839572238,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 69.43814796420975,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 148,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-6-flash:13a24e3021af753a",
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 35,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:14Z",
      "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": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1758.2226139935103,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 69.12714958998048,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:thinkingmachines-inkling:a1a9848a1d14b67e",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 37,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1751.0420667004444,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 67.94308497290339,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 70
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 276,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-5:2bf46853c4c2a3bc",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 119,
      "draws": 16,
      "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": 57,
      "max_score": null,
      "measured_at": "2026-08-21T15:53:02Z",
      "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": 276,
      "rating_method": "sequential_elo",
      "raw_elo": 1735.1859103033014,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 66.64176038754904,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.4376202060078436,
      "unilateral_faults": 0,
      "wins": 203
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:moonshotai-kimi-k2-7-code:0eac35852db14de0",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": 30,
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1716.3352365750259,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 64.14078623679886,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:meta-muse-spark-1-2:0ef600658249027b",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "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": "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": 19,
      "max_score": null,
      "measured_at": "2026-08-21T18:11:34Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1697.4882744755037,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 62.06040464059319,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 55
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 0,
      "draws": 27,
      "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": 59,
      "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": "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": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1672.9073139766474,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 59.23297694417742,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.895291237259062,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-luna:f9f63ab67ac1da8b",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "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-luna",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:23:24Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1659.815042678165,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "XHigh (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 58.34173612315974,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:meta-muse-spark-1-2:539f99e7c4c4b6ea",
      "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": "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": 33,
      "max_score": null,
      "measured_at": "2026-08-21T18:12:16Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1653.2616124943645,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 57.58895419336781,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-sol:92a27bf667504f91",
      "capped_draws": 20,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 20,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:14Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1652.9687749937566,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 57.5593474287059,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4:483e8409583d40a0",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": 23,
      "max_score": null,
      "measured_at": "2026-08-15T02:22:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1650.2502481709378,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 57.188133954793884,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-terra:75cc7f062ffaf091",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:23:24Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1623.2810218217542,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.77316499562428,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4:00c166645bf94fd4",
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 26,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:44:25Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1614.3353490460158,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "XHigh (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 53.907990168643416,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-5:1a25631bf54a6363",
      "capped_draws": 50,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "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": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-02T22:46:40Z",
      "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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1602.1188603960716,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.85326775023768,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 188,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4-nano:4caf0453cfb54e62",
      "capped_draws": 52,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 92,
      "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-5.4-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": 59,
      "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": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1591.1098460751618,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 51.39543114974306,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-8-max:644816d2bc8a5f5c",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 7,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 2,
      "max_score": null,
      "measured_at": "2026-08-22T18:02:47Z",
      "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": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1632.9497775865889,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.496905291659246,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 70.95786693528086,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:z-ai-glm-5-2:5ea14bc9644b6a2b",
      "capped_draws": 64,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 75,
      "draws": 64,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 31,
      "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": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1586.4595448981868,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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",
          "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.42797378512286,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.697319232624107,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 314,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-6-flash:b4583ef7c04d45cd",
      "capped_draws": 107,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 124,
      "draws": 107,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 90,
      "max_score": null,
      "measured_at": "2026-08-22T23:22:38Z",
      "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": 314,
      "rating_method": "sequential_elo",
      "raw_elo": 1561.8662103116926,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 49.370612946586476,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-sol:7aebae84d73affb6",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "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-5.6-sol",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-02T23:32:31Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1532.272527260815,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "None (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.402421187694905,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 43
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 196,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4-nano:8753e840d1cee063",
      "capped_draws": 95,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 97,
      "draws": 95,
      "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": 45,
      "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": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1526.837067851132,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.966275272568765,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.695604130687789,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 478,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:o3:1084c60ee563e860",
      "capped_draws": 191,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 188,
      "draws": 191,
      "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": 145,
      "max_score": null,
      "measured_at": "2026-08-22T14:19:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 478,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.6216092291434,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.110057009595636,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-pro:a4cf9c7798e0d7dc",
      "capped_draws": 82,
      "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": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T03:56:58Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.1908415956534,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.09650651851254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:minimax-minimax-m3:6639861dd7b73e51",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 49,
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.5181338037046,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.08815494051834,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 40
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:stealth-ox-alpha:fe3b437dca2c4367",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 21,
      "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": "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": 7,
      "max_score": null,
      "measured_at": "2026-08-23T14:12:04Z",
      "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": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1570.5181600374551,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.02085235239664,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-5:3449c1aec50b70b2",
      "capped_draws": 53,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "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": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T21:46:23Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.4249105169813,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.91288442671314,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-terra:08cc40e91e1568bf",
      "capped_draws": 53,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 53,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:28:10Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.0543554717117,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.442997530903185,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-sonnet-5:a86621e2793b5dec",
      "capped_draws": 34,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 34,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-08-15T01:49:26Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.505798798824,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking 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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Thinking disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.22865839038472,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1,
      "attempted_matches": 103,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4:672219b99ff5a80c",
      "capped_draws": 53,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 53,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-08-21T19:14:11Z",
      "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": 103,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.262264289942,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.16979011364343,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.279033784546012,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-8-max:a791831295f0ee80",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 7,
      "draws": 13,
      "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": 0,
      "max_score": null,
      "measured_at": "2026-08-21T20:35:50Z",
      "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": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1535.5507689243868,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.11898397519311,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4:ef3925c3f5fdbb2d",
      "capped_draws": 39,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "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",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T06:08:42Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.125133604714,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.03561880449786,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:o3:f70fd8105d3dfec2",
      "capped_draws": 63,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 63,
      "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": 32,
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.6955904890767,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.04547015939034,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:tencent-hy3-preview:173ea133649c5bcd",
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "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": "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": 45,
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.8491002180717,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.12488588080784,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-7-max:fa240f0afd3eda59",
      "capped_draws": 76,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 76,
      "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": 31,
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.8004114495486,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.640629833593636,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4:c42a41ea59ccc1f7",
      "capped_draws": 74,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 74,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:41:54Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.7096875631094,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "None (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.429097626212254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-1-flash-lite:4c9cdde1729642af",
      "capped_draws": 40,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "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": "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": 51,
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.8578660442124,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.2403624207267,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4-mini:e296afd987da0af3",
      "capped_draws": 41,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 41,
      "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": 38,
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.5819424274005,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.04910404429471,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 35
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:stealth-ox-alpha:6719f8157bcde29f",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 21,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 13,
      "max_score": null,
      "measured_at": "2026-08-23T14:11:53Z",
      "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": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.424913229797,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.63090211679806,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-sonnet-5:906c16e3480819c2",
      "capped_draws": 55,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 55,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:23:14Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.5092315776758,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (historical request variant 3)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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-variant-3",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh (historical request variant 3)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-3",
        "reasoning_bucket_label": "XHigh (historical request variant 3)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-3"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-3",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.019299747841444,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:openai-gpt-oss-120b:f9a4cf175428ff96",
      "capped_draws": 86,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 86,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:33:45Z",
      "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": 1421.642551452285,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.70371174356963,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-5:53d4c02c8a9496db",
      "capped_draws": 83,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "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-5.5",
        "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": 19,
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.0693276623153,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.342294273323965,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:tencent-hy3-preview:7ef07d2849ca4d92",
      "capped_draws": 90,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 90,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 21,
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.9497965630508,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.26644030755798,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-4-1:731bd482a4919a05",
      "capped_draws": 79,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "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-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": 16,
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.4565971654238,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.21527625173018,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5:16f7def69ce10ccd",
      "capped_draws": 66,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "draws": 66,
      "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": 32,
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.3165817886681,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.20242036213885,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemma-4-31b-it:e2b2f6f0f78a1f3f",
      "capped_draws": 94,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "draws": 94,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 21,
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.9221194161503,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.12535861356842,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:be72f75fe8d3007b",
      "capped_draws": 78,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 78,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 5,
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.0047853601131,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.06110906673491,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-7-plus:e4e482b5c34e690f",
      "capped_draws": 94,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 94,
      "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": 20,
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.39305533373,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.007945969500966,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:minimax-minimax-m3:6f48906184a5bdb8",
      "capped_draws": 90,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 90,
      "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": 19,
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.9719926684977,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 33.69443719624106,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-luna:89e8232b6c428839",
      "capped_draws": 89,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 89,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:17:39Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.463867477643,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 33.610693090596705,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 17,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:thinkingmachines-inkling-small:c4a079d6b58a2c73",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 8,
      "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": "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": 1,
      "max_score": null,
      "measured_at": "2026-08-22T23:00:21Z",
      "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": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.4221652498795,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 33.608426961121125,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 74.10113019775793,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-sonnet-5:e2e304f6cedf7237",
      "capped_draws": 85,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 85,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:33:59Z",
      "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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.0267536166316,
      "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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 33.12886059328138,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:a3e60c7aa64704be",
      "capped_draws": 74,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "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": "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": 27,
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.0071008564112,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.99164981596408,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:z-ai-glm-5-2:f14efcbac580ffaa",
      "capped_draws": 66,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "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": "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": 11,
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1412.1516499621744,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.90140047086365,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:x-ai-grok-build-0-1:55f4f20890a40d69",
      "capped_draws": 93,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 93,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "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": 15,
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.4257773948275,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.89912071233677,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-flash:865c6d4e9c2ee4b8",
      "capped_draws": 88,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 88,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-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": 18,
      "max_score": null,
      "measured_at": "2026-08-05T04:55:50Z",
      "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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.0594040768221,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.82885250240368,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:cohere-north-mini-code:4a23759df70ab26b",
      "capped_draws": 96,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 96,
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.3296396091612,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.78188345286514,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:nex-agi-nex-n2-pro:b04b6e7c11ec4633",
      "capped_draws": 96,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "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": "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": 14,
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1403.0243582764076,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.69008544176368,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-luna:fd12531a88a47fab",
      "capped_draws": 89,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 89,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:41:40Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1403.3240921912495,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "None (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.68533383456862,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-8-max:7b21229bd01e0b5e",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 8,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 4,
      "max_score": null,
      "measured_at": "2026-08-23T02:42:56Z",
      "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": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.2655519062441,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.3302819181756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 70.95786693528086,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 15,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:thinkingmachines-inkling-small:6603774c29b8a046",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 7,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 3,
      "max_score": null,
      "measured_at": "2026-08-21T20:21:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 15,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.0832035786366,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.187114460064755,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 81.25,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-flash:1ebaee0e9d08b232",
      "capped_draws": 77,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 77,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:43:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.1860928220167,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.16586642400081,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:openai-gpt-oss-120b:d658f92b65107751",
      "capped_draws": 67,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "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": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:53:14Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1400.2862698488254,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.10258545358184,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-7-max:a92ef5f3c3f212e3",
      "capped_draws": 76,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 76,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 30,
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1397.181675768906,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.09937241616148,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4-mini:9285646640165917",
      "capped_draws": 77,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "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-5.4-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": 13,
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1400.3144399361822,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.01522338949161,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 2,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-4-8:8ccf8977401d94db",
      "capped_draws": 84,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 84,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": 21,
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1395.7974788159802,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.959425881493154,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 196,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:94c7956182cf2d89",
      "capped_draws": 132,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 95,
      "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": "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": 49,
      "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": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1397.872639678978,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.93763264773245,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.571294191973962,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-5:235a446f3a9f9cd3",
      "capped_draws": 74,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "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": "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": 16,
      "max_score": null,
      "measured_at": "2026-07-31T03:36:08Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1393.1451787133317,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.33622181797477,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-terra:0983009cb1ffeee4",
      "capped_draws": 74,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 74,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T07:10:17Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.0357740645313,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.292461943857255,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 2,
      "wins": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 164,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-flash:dac448fbfe2a5737",
      "capped_draws": 144,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 82,
      "draws": 144,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 16,
      "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": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1394.044883352306,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.180776324860656,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.144085005109797,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:meituan-longcat-2-0:45102822fc5f9296",
      "capped_draws": 200,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 109,
      "draws": 200,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 22,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:26Z",
      "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": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1386.927401056984,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.146167032179893,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.6751283820590555,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 14,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:thinkingmachines-inkling-small:f1451a0a6af20650",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 6,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 4,
      "max_score": null,
      "measured_at": "2026-08-21T20:35:50Z",
      "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": 14,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.7011179104888,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.109189972494256,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 85.34944487358055,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 192,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:moonshotai-kimi-k3:6a00f2f5a49a8584",
      "capped_draws": 134,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "draws": 134,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 46,
      "max_score": null,
      "measured_at": "2026-08-21T19:14:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1378.0442055713736,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.092003821784623,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-pro:d03a9ec0db9a8b52",
      "capped_draws": 65,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 65,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:23:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1387.905101445435,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.850811557145292,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:poolside-laguna-s-2-1:533b6103a5973424",
      "capped_draws": 195,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 109,
      "draws": 195,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1383.4836426691504,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.797992553400974,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.6751283820590555,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-5:024b37c390436d5a",
      "capped_draws": 71,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "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": "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": 5,
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1390.6857995210323,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.7311375060473,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:stepfun-step-3-7-flash:0e0f63cf65826515",
      "capped_draws": 70,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 70,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 21,
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1385.5425180436987,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.56756963106926,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-1-flash-lite:78a7cfd3a790e8a8",
      "capped_draws": 72,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 72,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 28,
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1381.0312376325182,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.395424278997872,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-sonnet-5:73f1b29a5c45562d",
      "capped_draws": 52,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 52,
      "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": 29,
      "max_score": null,
      "measured_at": "2026-08-21T15:02:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1384.3413005388531,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.352921291303954,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 318,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:inclusionai-ling-3-0-flash:1ed2a890413ad375",
      "capped_draws": 272,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 118,
      "draws": 272,
      "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": 37,
      "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": 314,
      "rating_method": "sequential_elo",
      "raw_elo": 1371.6131397638803,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.13544711494835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-sonnet-5:3d227889fd8fad8f",
      "capped_draws": 108,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 108,
      "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": "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": 5,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:08Z",
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1375.919697911772,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking 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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Thinking disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.049440212697277,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 311,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:meituan-longcat-2-0:bed5035a5082adf8",
      "capped_draws": 97,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 120,
      "draws": 97,
      "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": 154,
      "max_score": null,
      "measured_at": "2026-08-21T19:14:48Z",
      "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": 311,
      "rating_method": "sequential_elo",
      "raw_elo": 1369.8300630344902,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.932069292243508,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 346,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-6-flash:b574aaabaed70f28",
      "capped_draws": 238,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 129,
      "draws": 238,
      "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": 92,
      "max_score": null,
      "measured_at": "2026-08-23T00:15:43Z",
      "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": 346,
      "rating_method": "sequential_elo",
      "raw_elo": 1363.5371582184212,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.47044083995327,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 95,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4:cea8a68bd875deb9",
      "capped_draws": 55,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "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",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-21T19:14:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 95,
      "rating_method": "sequential_elo",
      "raw_elo": 1369.4284056978859,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "None (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.00442814379102,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.281036307982882,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:4b9c2bdb10b14302",
      "capped_draws": 75,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "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": "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": 25,
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1367.9946417839965,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.00219316035198,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 344,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:poolside-laguna-s-2-1:07eac22bdea1b9b3",
      "capped_draws": 235,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 132,
      "draws": 235,
      "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": 95,
      "max_score": null,
      "measured_at": "2026-08-22T11:41:58Z",
      "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": 344,
      "rating_method": "sequential_elo",
      "raw_elo": 1354.0937791457006,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 28.50687633728013,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 343,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-5-flash-lite:55634764b9427e4e",
      "capped_draws": 237,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 127,
      "draws": 237,
      "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": 92,
      "max_score": null,
      "measured_at": "2026-08-23T12:51:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 343,
      "rating_method": "sequential_elo",
      "raw_elo": 1349.6849491452738,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 28.056667626445826,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:mistralai-mistral-medium-3-5:6deb1b60bb205df7",
      "capped_draws": 92,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "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": "mistralai/mistral-medium-3-5",
        "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": 22,
      "max_score": null,
      "measured_at": "2026-08-05T04:49:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1354.8843322134849,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 27.922700568650274,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 186,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-4-5:9f0371e603fb81bd",
      "capped_draws": 99,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 65,
      "draws": 99,
      "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": 70,
      "max_score": null,
      "measured_at": "2026-08-21T15:41:34Z",
      "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": 186,
      "rating_method": "sequential_elo",
      "raw_elo": 1346.2739670506865,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 27.83360360167963,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 163,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:o3:29970c6bc7db3c37",
      "capped_draws": 111,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "draws": 111,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-08-23T12:51:52Z",
      "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": 163,
      "rating_method": "sequential_elo",
      "raw_elo": 1346.4376685189152,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 27.649580485211807,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-sol:683e7f269aa1d12e",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 13,
      "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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:22:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1356.219884706978,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 2)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-2",
        "reasoning_bucket_label": "XHigh (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 27.509760361553635,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:cohere-north-mini-code:959513c67c4e5ee3",
      "capped_draws": 50,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 34,
      "draws": 80,
      "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": 22,
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1368.1606981960256,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 27.151591469186677,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 28.604176007868134,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 178,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:thinkingmachines-inkling:281eafa14f6ff011",
      "capped_draws": 103,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 103,
      "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": 71,
      "max_score": null,
      "measured_at": "2026-08-21T19:14:04Z",
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1337.923250186877,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.923956847273455,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5:3bb27dbc092c7ff2",
      "capped_draws": 56,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 56,
      "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": 26,
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1347.8497544240654,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.71088363179663,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 8
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 320,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-5-flash-lite:0bab1c3ea19c7cb7",
      "capped_draws": 217,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 120,
      "draws": 217,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 90,
      "max_score": null,
      "measured_at": "2026-08-23T02:42:56Z",
      "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": 320,
      "rating_method": "sequential_elo",
      "raw_elo": 1334.025892170579,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.364688046126368,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 170,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-5-flash-lite:5943a501fa6113ab",
      "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": "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": 61,
      "max_score": null,
      "measured_at": "2026-08-21T18:21:11Z",
      "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": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1329.5503292837363,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.007530314351136,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 157,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:thinkingmachines-inkling:b27963da4b6944f2",
      "capped_draws": 96,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": "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": 50,
      "max_score": null,
      "measured_at": "2026-08-21T18:11:13Z",
      "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": 157,
      "rating_method": "sequential_elo",
      "raw_elo": 1328.7976684792145,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 25.806720683180234,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 28,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:stealth-ox-alpha:dfb3dd7361cfa1a2",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 14,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 17,
      "max_score": null,
      "measured_at": "2026-08-23T14:12:04Z",
      "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": 28,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.0853900991224,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 25.587373276225822,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 85.34944487358055,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-5-flash:5712a3e29dc27925",
      "capped_draws": 68,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "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-3.5-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": 22,
      "max_score": null,
      "measured_at": "2026-08-03T02:54:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1332.5013086471351,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 25.159108940712393,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-luna:29e28a5adce9180a",
      "capped_draws": 55,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 55,
      "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": 32,
      "max_score": null,
      "measured_at": "2026-08-23T09:38:55Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1323.5572279214625,
      "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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "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": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 24.254835093911925,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-luna:e05ef4cc93414f96",
      "capped_draws": 51,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 51,
      "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": 35,
      "max_score": null,
      "measured_at": "2026-08-21T18:10:38Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1316.0178733440812,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh (historical request variant 1)",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive-variant-1",
        "reasoning_bucket_label": "XHigh (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-intensive-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 23.445214369711753,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-5:35035a0b78826dbc",
      "capped_draws": 60,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "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": 34,
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1302.9215821989426,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 22.301716366131743,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 158,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:stepfun-step-3-7-flash:b2de164dfb65fa47",
      "capped_draws": 104,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 104,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 54,
      "max_score": null,
      "measured_at": "2026-08-23T09:38:55Z",
      "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": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1292.208218512245,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 22.117549019522556,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-5-flash:2637a22cd82f12e9",
      "capped_draws": 62,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 62,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:58:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1296.1001435676862,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 21.612048110556422,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 158,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:openai-gpt-oss-120b:7785ef5b91a441ff",
      "capped_draws": 94,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "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": "openai/gpt-oss-120b",
        "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": 60,
      "max_score": null,
      "measured_at": "2026-08-23T02:22:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1270.3817645663387,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.910827940292407,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-5:32918e3c3e0fca83",
      "capped_draws": 45,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "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": "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": 46,
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1275.0559963930348,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.44142277101602,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:nex-agi-nex-n2-pro:a8c61d4550659ad0",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 71,
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1194.9426957801345,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 11.297346143143717,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-luna:15a0f0a09f9eb8e5",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 12,
      "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": 74,
      "max_score": null,
      "measured_at": "2026-08-22T11:52:09Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1083.655118803301,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None (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": "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-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "None (historical request variant 1)",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 4
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:claude-fable-5:7f49308e40ed3ed5",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 16,
        "cost_basis_counts": {
          "local_list_price_estimate": 19
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 1.91725,
        "mean": 1.043635625,
        "median": 0.8756600000000001,
        "min": 0.33027,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 19
        },
        "run_count": 16,
        "token_priced_attempt_count": 19,
        "total": 16.69817
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "eligibility_flag": false,
      "entry_count": 15,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 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": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04"
      ],
      "infra_failures_excluded": 4,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:44:21Z",
      "losses": null,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 55.133363671974216,
      "model_code_failure_rate": 0.0625,
      "model_code_failures": 1,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 75.13438841167155,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 41,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:claude-opus-5:e3a8c6d4d5f3bdeb",
      "capped_draws": 0,
      "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": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "2026-08-15T00:11:21Z",
      "losses": null,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 51.08859351407519,
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1784.826606311556,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 73.125125657378,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5-6-sol:355993239c1ccc35",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 48,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_standard_estimate": 52
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 6.83719875,
        "mean": 1.9681597916666664,
        "median": 0.3360778125,
        "min": 0.09558187500000001,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 52
        },
        "run_count": 50,
        "token_priced_attempt_count": 52,
        "total": 94.89133875
      },
      "codegen_evaluated_cells": 26,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "eligibility_flag": true,
      "entry_count": 48,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 23,
      "first_pass_rate": 0.8846153846153846,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 24,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T05:21:14Z",
      "losses": null,
      "max_score": 99.52317300196941,
      "measured_at": null,
      "min_score": 26.469312004278905,
      "model_code_failure_rate": 0.07692307692307693,
      "model_code_failures": 2,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1664.8534300443916,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 1,
      "repaired_rate": 0.038461538461538464,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 61.72068956858967,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5-4:b646b36fcd253b5f",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 47,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_standard_estimate": 55
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 2.44992,
        "mean": 0.8555469270833335,
        "median": 0.40353625,
        "min": 0.06869,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 55
        },
        "run_count": 48,
        "token_priced_attempt_count": 55,
        "total": 41.0662525
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "eligibility_flag": true,
      "entry_count": 47,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "2026-08-23T08:23:52Z",
      "losses": null,
      "max_score": 96.95590676313576,
      "measured_at": null,
      "min_score": 18.245710919802534,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1643.4560618639107,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 56.88052298150171,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:x-ai-grok-4-5:d65de196562f343c",
      "capped_draws": 0,
      "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": 1.6998543999999998
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "2026-08-23T13:45:16Z",
      "losses": null,
      "max_score": 89.63424632680322,
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1598.8543271207063,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 53.52834806313026,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 22,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5-5:6c8c03d567738842",
      "capped_draws": 0,
      "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": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": null,
      "max_score": 92.32704029193545,
      "measured_at": null,
      "min_score": 22.09524395964808,
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1603.1764093719855,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 52.32719281804168,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 22,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:claude-opus-4-8:66e9f46ea7415508",
      "capped_draws": 0,
      "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": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "2026-08-05T04:35:38Z",
      "losses": null,
      "max_score": 81.45539006883097,
      "measured_at": null,
      "min_score": 16.344385607773184,
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1598.1595075312707,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 52.170096342650396,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 42,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:google-gemini-3-6-flash:6aba70247d100ab2",
      "capped_draws": 0,
      "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": 12.701101349999998
      },
      "codegen_evaluated_cells": 48,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "2026-08-23T13:45:16Z",
      "losses": null,
      "max_score": 90.98102138726986,
      "measured_at": null,
      "min_score": 16.214567763911244,
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1595.1529771953915,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 50.924643935954116,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:google-gemini-3-5-flash:c324fc4c43d7c8e1",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 20,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 51
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.6921525,
        "mean": 0.30153312499999996,
        "median": 0.335163,
        "min": 0.025422,
        "recorded_attempt_count": 51,
        "run_count": 24,
        "total": 7.236795
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 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"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:04:52Z",
      "losses": null,
      "max_score": 86.87039539493097,
      "measured_at": null,
      "min_score": 21.612048110556422,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "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/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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 14,
      "repaired_rate": 0.875,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 49.976468612854845,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 21,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:moonshotai-kimi-k3:601623cc06431dd6",
      "capped_draws": 0,
      "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": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [
        "GB2-08"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T17:46:55Z",
      "losses": null,
      "max_score": 96.03018425662745,
      "measured_at": null,
      "min_score": 19.758668893473487,
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.167591474086,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 48.93950951309686,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 17,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:meta-muse-spark-1-2:3667fca8056828bb",
      "capped_draws": 0,
      "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": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": [
        "below_generation_quality_threshold"
      ],
      "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": "2026-08-23T02:44:09Z",
      "losses": null,
      "max_score": 80.14955515143204,
      "measured_at": null,
      "min_score": 16.50878695816217,
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.6588905658618,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 47.20110944537896,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5-6-terra:97de4d20c6c50836",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_standard_estimate": 32
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 12.137519999999999,
        "mean": 2.8005991666666663,
        "median": 0.15809499999999999,
        "min": 0.0542775,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 32
        },
        "run_count": 25,
        "token_priced_attempt_count": 32,
        "total": 67.27386999999999
      },
      "codegen_evaluated_cells": 25,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 17,
      "first_pass_rate": 0.68,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_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",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 24,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:18:32Z",
      "losses": null,
      "max_score": 72.91627837470821,
      "measured_at": null,
      "min_score": 25.970772760443374,
      "model_code_failure_rate": 0.04,
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1533.5058810979972,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 7,
      "repaired_rate": 0.28,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 47.10551480154788,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:claude-opus-4-5:7a31aface18eaea9",
      "capped_draws": 0,
      "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": 11.203785000000003
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-21T20:34:32Z",
      "losses": null,
      "max_score": 82.15300774815739,
      "measured_at": null,
      "min_score": 13.32462959183295,
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.444991596441,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 46.6030257414644,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 26,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:z-ai-glm-5-2:b52271e32d7b710c",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 26,
        "cell_count": 17,
        "cost_basis_counts": {
          "provider_reported": 47
        },
        "evidence_basis": "Provider-reported",
        "max": 0.14831665,
        "mean": 0.04690495967823529,
        "median": 0.030447832,
        "min": 0.0106770175,
        "recorded_attempt_count": 47,
        "run_count": 26,
        "total": 1.06760263506
      },
      "codegen_evaluated_cells": 26,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 11,
      "first_pass_rate": 0.4230769230769231,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_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",
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T14:35:20Z",
      "losses": null,
      "max_score": 65.44552694683463,
      "measured_at": null,
      "min_score": 16.009458011887702,
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.0355458952456,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 15,
      "repaired_rate": 0.5769230769230769,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 45.31057524046488,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:claude-sonnet-5:351ed472be23eda4",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 50,
        "cell_count": 24,
        "cost_basis_counts": {
          "estimated": 1,
          "local_list_price_estimate": 52,
          "provider_dashboard_reconciled": 1
        },
        "evidence_basis": "Combined: Provider-reported + Recorded attempt + Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.48068,
        "mean": 0.1662809027777778,
        "median": 0.07628299999999999,
        "min": 0.050688,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 2,
          "boardgame-list-prices-2026-08-08": 51
        },
        "recorded_attempt_count": 2,
        "run_count": 51,
        "token_priced_attempt_count": 52,
        "total": 8.91507
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "eligibility_flag": true,
      "entry_count": 50,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 16,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T12:40:55Z",
      "losses": null,
      "max_score": 61.83534732022994,
      "measured_at": null,
      "min_score": 21.114044974233778,
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1506.8058899050206,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 44.18507013062426,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5:509525aafb482b3d",
      "capped_draws": 0,
      "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": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": null,
      "max_score": 66.00620122264021,
      "measured_at": null,
      "min_score": 20.557432544949897,
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 43.306651750904074,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 13,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:deepseek-deepseek-v4-pro:d46bf919cbe90971",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 13,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 28
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.10909930499999998,
        "mean": 0.049205097625000006,
        "median": 0.034298199,
        "min": 0.005612805,
        "recorded_attempt_count": 28,
        "run_count": 16,
        "total": 0.787281562
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 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": [
        "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": "2026-08-05T05:11:41Z",
      "losses": null,
      "max_score": 74.1333084252556,
      "measured_at": null,
      "min_score": 21.894015414373516,
      "model_code_failure_rate": 0.1875,
      "model_code_failures": 3,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 8,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 41.512537943055854,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:moonshotai-kimi-k2-7-code:3b6469f485258e46",
      "capped_draws": 0,
      "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": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": null,
      "max_score": 64.14078623679886,
      "measured_at": null,
      "min_score": 23.349084470138546,
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 41.31960163911211,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-4-1-nano:bf2b00ecdde1f74d",
      "capped_draws": 0,
      "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-2026-08-08": 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": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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",
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-14T15:31:41Z",
      "losses": null,
      "max_score": 40.511310783890416,
      "measured_at": null,
      "min_score": 40.511310783890416,
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 40.511310783890416,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:qwen-qwen3-7-max:2295a106326bfd7d",
      "capped_draws": 0,
      "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": 0.9112224999999997
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": null,
      "max_score": 72.79240290081826,
      "measured_at": null,
      "min_score": 15.965232157159793,
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 40.193769211935795,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:xiaomi-mimo-v2-5-pro:1f2ff8329154ac84",
      "capped_draws": 0,
      "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": 1.2846227784000002
      },
      "codegen_evaluated_cells": 15,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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",
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:17:07Z",
      "losses": null,
      "max_score": 65.17750853680307,
      "measured_at": null,
      "min_score": 25.222210730949445,
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 39.67345826674859,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-4-1:d5dcb828dbee1dd0",
      "capped_draws": 0,
      "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": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": null,
      "max_score": 54.37710879884957,
      "measured_at": null,
      "min_score": 17.324048509285905,
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 39.175380343627474,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:qwen-qwen3-8-max:3bcc7f6323eff7b9",
      "capped_draws": 0,
      "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": 6.452749999999998
      },
      "codegen_evaluated_cells": 26,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "eligibility_flag": false,
      "entry_count": 23,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [
        "GB2-02",
        "GB2-06",
        "GB2-08"
      ],
      "infra_failures_excluded": 3,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T01:51:58Z",
      "losses": null,
      "max_score": 65.34857672458816,
      "measured_at": null,
      "min_score": 7.491362721335916,
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1528.4112972594364,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 38.169396763757256,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5-4-mini:55f0d0ca5e9d66ef",
      "capped_draws": 0,
      "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": 22
        },
        "recorded_attempt_count": 2,
        "run_count": 18,
        "token_priced_attempt_count": 22,
        "total": 5.1688104
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": null,
      "max_score": 59.73623054906832,
      "measured_at": null,
      "min_score": 7.8623797518037435,
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 38.0256925811143,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5-6-luna:0ccf02fcc67f023e",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 48,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_standard_estimate": 53
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 0.51553995,
        "mean": 0.11897204999999998,
        "median": 0.006426525,
        "min": 0.0036738749999999996,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 53
        },
        "run_count": 50,
        "token_priced_attempt_count": 53,
        "total": 6.1934650499999995
      },
      "codegen_evaluated_cells": 26,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "eligibility_flag": true,
      "entry_count": 48,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 22,
      "first_pass_rate": 0.8461538461538461,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 24,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T12:40:55Z",
      "losses": null,
      "max_score": 80.44715581991792,
      "measured_at": null,
      "min_score": 10.864694550855324,
      "model_code_failure_rate": 0.07692307692307693,
      "model_code_failures": 2,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.9936524849074,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 2,
      "repaired_rate": 0.07692307692307693,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 37.901891204021624,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:x-ai-grok-build-0-1:657efc023ad7cc85",
      "capped_draws": 0,
      "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": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": null,
      "max_score": 63.41974151718129,
      "measured_at": null,
      "min_score": 21.669541208427077,
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 37.88184486713599,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5-4-nano:21e1db315087268e",
      "capped_draws": 0,
      "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": 55
        },
        "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": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": null,
      "max_score": 61.40570645858217,
      "measured_at": null,
      "min_score": 13.75796311182292,
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 36.67448962129495,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 29,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:o3:54cad6d3f7756427",
      "capped_draws": 0,
      "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": 56
        },
        "recorded_attempt_count": 40,
        "run_count": 48,
        "token_priced_attempt_count": 29,
        "total": 4.2016860000000005
      },
      "codegen_evaluated_cells": 48,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "2026-08-23T12:51:52Z",
      "losses": null,
      "max_score": 59.630586714276724,
      "measured_at": null,
      "min_score": 7.743053185185025,
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.3310737996421,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 36.11798355657051,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 79,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:stealth-ox-alpha:2017c74462701082",
      "capped_draws": 0,
      "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": 0,
      "draws": null,
      "eligibility_flag": true,
      "entry_count": 66,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "2026-08-23T14:12:18Z",
      "losses": null,
      "max_score": 50.86244134919709,
      "measured_at": null,
      "min_score": 3.872072017351666,
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.8057114160026,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 35.710303680479946,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 13,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:tencent-hy3-preview:f8fa673b07fb084d",
      "capped_draws": 0,
      "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": 0.041725613
      },
      "codegen_evaluated_cells": 17,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": null,
      "max_score": 71.07282896064237,
      "measured_at": null,
      "min_score": 13.758406271721789,
      "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": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 35.19742419481098,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 43,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:google-gemini-3-5-flash-lite:1e1b77d01aa6fd1f",
      "capped_draws": 0,
      "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": 1.8519748999999996
      },
      "codegen_evaluated_cells": 48,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "2026-08-23T12:51:52Z",
      "losses": null,
      "max_score": 69.37028762269674,
      "measured_at": null,
      "min_score": 9.276903456466506,
      "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": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.4797951510377,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 33.39036111727063,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:qwen-qwen3-7-plus:a67ab29b6f7f0b5a",
      "capped_draws": 0,
      "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": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": null,
      "max_score": 70.50103787240695,
      "measured_at": null,
      "min_score": 4.247286587507169,
      "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": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 33.27997174457582,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 10,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:google-gemma-4-31b-it:54dd73921471ddad",
      "capped_draws": 0,
      "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": 0.06253070000000001
      },
      "codegen_evaluated_cells": 14,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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",
        "below_generation_quality_threshold"
      ],
      "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": null,
      "max_score": 55.00038838965367,
      "measured_at": null,
      "min_score": 17.377509992236185,
      "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": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 33.03930197291725,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:thinkingmachines-inkling-small:e5c2210ece87e3e8",
      "capped_draws": 0,
      "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": 0.5373186000000001
      },
      "codegen_evaluated_cells": 28,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T05:50:12Z",
      "losses": null,
      "max_score": 54.116030920939295,
      "measured_at": null,
      "min_score": 11.574430248545012,
      "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": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.8928182027225,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 32.377537246167044,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 27,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:deepseek-deepseek-v4-flash:fb6f94455ec4d370",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 27,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 49
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.0221782524,
        "mean": 0.005150116054583333,
        "median": 0.00311373,
        "min": 0.0013289177,
        "recorded_attempt_count": 49,
        "run_count": 32,
        "total": 0.14908945064
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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"
      ],
      "first_pass_admitted": 18,
      "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": [
        "untested_or_ineligible_settings"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:23:15Z",
      "losses": null,
      "max_score": 72.03816050961174,
      "measured_at": null,
      "min_score": 16.918306920549412,
      "model_code_failure_rate": 0.15625,
      "model_code_failures": 5,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1399.0000378854681,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 31.954685717749697,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 23,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:poolside-laguna-s-2-1:aa9d42ace8f050f0",
      "capped_draws": 0,
      "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": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "2026-08-23T00:33:40Z",
      "losses": null,
      "max_score": 54.815141934474596,
      "measured_at": null,
      "min_score": 18.971051988167996,
      "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": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 31.820507612172108,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:xiaomi-mimo-v2-5:ba2faefd47e3050c",
      "capped_draws": 0,
      "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": 0.00169122,
        "recorded_attempt_count": 108,
        "run_count": 56,
        "total": 0.7524538072
      },
      "codegen_evaluated_cells": 36,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": null,
      "max_score": 55.77389183234963,
      "measured_at": null,
      "min_score": 17.065325253973946,
      "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": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.6983142465065,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 31.575394430852445,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 21,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:nvidia-nemotron-3-ultra-550b-a55b:14c1d11c89476159",
      "capped_draws": 0,
      "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": 1.2116408500000002
      },
      "codegen_evaluated_cells": 34,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": null,
      "max_score": 60.46921496514469,
      "measured_at": null,
      "min_score": 10.757672736091521,
      "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": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.650827570517,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 31.19955846631954,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 13,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:minimax-minimax-m3:bb38eb0c97be722d",
      "capped_draws": 0,
      "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": 0.7875583200000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": null,
      "max_score": 49.061655826617994,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.1875,
      "model_code_failures": 3,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 31.190972439089,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 26,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:meituan-longcat-2-0:75c0c8b0e77d80fa",
      "capped_draws": 0,
      "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": 1.60040646
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "2026-08-22T06:50:55Z",
      "losses": null,
      "max_score": 56.21511165223179,
      "measured_at": null,
      "min_score": 14.601235431191899,
      "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": 40,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 31.170607687823995,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 13,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:stepfun-step-3-7-flash:0151b4f3ef2d8a82",
      "capped_draws": 0,
      "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": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "2026-08-19T15:24:00Z",
      "losses": null,
      "max_score": 50.91082045936282,
      "measured_at": null,
      "min_score": 12.522239497043625,
      "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": 41,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1400.1695292456404,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 29.532585278113142,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 27,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:thinkingmachines-inkling:96d334950f7b14e7",
      "capped_draws": 0,
      "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": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "2026-08-22T23:41:33Z",
      "losses": null,
      "max_score": 67.94308497290339,
      "measured_at": null,
      "min_score": 8.04764389452622,
      "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": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1355.3834678014034,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 28.016436981467752,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 19,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:openai-gpt-oss-120b:1ff5d67f22d3eaab",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 19,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 48
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.01660212,
        "mean": 0.00430918425,
        "median": 0.0025298300000000003,
        "min": 0.00045831,
        "recorded_attempt_count": 48,
        "run_count": 24,
        "total": 0.10342042200000001
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "eligibility_flag": true,
      "entry_count": 19,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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",
        "GB2-07"
      ],
      "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": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T05:21:37Z",
      "losses": null,
      "max_score": 67.82204727657161,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.20833333333333334,
      "model_code_failures": 5,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1385.4055093520121,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 13,
      "repaired_rate": 0.5416666666666666,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 27.468242352636967,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:nex-agi-nex-n2-pro:a1783d1581f6f6d9",
      "capped_draws": 0,
      "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": 3.40579925
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": null,
      "max_score": 60.50605278337446,
      "measured_at": null,
      "min_score": 11.297346143143717,
      "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": 44,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 27.303167692125538,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:cohere-north-mini-code:a91d2017566aaf6e",
      "capped_draws": 0,
      "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": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:19:01Z",
      "losses": null,
      "max_score": 47.666905146048265,
      "measured_at": null,
      "min_score": 20.068456528448355,
      "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": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 26.00533205586351,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:google-gemini-3-1-flash-lite:0903ce17ebd3d72b",
      "capped_draws": 0,
      "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": 0.34809300000000004
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": null,
      "max_score": 44.84292897073299,
      "measured_at": null,
      "min_score": 0.0,
      "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": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": 1227.3685847388876,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 24.46661762026912,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:mistralai-mistral-medium-3-5:a9c28fc18da0cc0b",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 28
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 9,
        "max": 0.3927285,
        "mean": 0.116635875,
        "median": 0.0747585,
        "min": 0.0223935,
        "recorded_attempt_count": 28,
        "run_count": 17,
        "total": 2.2589024999999996
      },
      "codegen_evaluated_cells": 17,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": null,
      "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": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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",
        "GB2-08"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.23529411764705882,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_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": "2026-08-05T05:02:41Z",
      "losses": null,
      "max_score": 39.8933469399602,
      "measured_at": null,
      "min_score": 11.379446013072632,
      "model_code_failure_rate": 0.5294117647058824,
      "model_code_failures": 9,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": 47,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 23.060639624246463,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:overall:inclusionai-ling-3-0-flash:879c7abb2fdbd104",
      "capped_draws": 0,
      "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": 0,
      "draws": null,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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"
      ],
      "infra_excluded_game_aliases": [
        "GB2-05"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:41:59Z",
      "losses": null,
      "max_score": 41.40501950685979,
      "measured_at": null,
      "min_score": 12.133934164094017,
      "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": 48,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 0,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 22.88330140834788,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": null
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:claude-opus-5:f836f90d8fb9ff19",
      "capped_draws": 0,
      "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": 7.138875
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 76.02497290363772,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 185,
      "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": 241,
      "max_score": 95.92764370282903,
      "measured_at": null,
      "min_score": 52.394609038466754,
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1358,
      "rating_method": "sequential_elo",
      "raw_elo": 1794.0569911901882,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 73.52893696868458,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 932
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:claude-fable-5:0d812a1d2c768408",
      "capped_draws": 0,
      "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": 0.6981,
        "mean": 0.5046499999999999,
        "median": 0.511355,
        "min": 0.33027,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 4.0371999999999995
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 68.70642652869618,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 69,
      "eligibility_flag": true,
      "entry_count": 7,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": 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": "2026-08-05T04:34:24Z",
      "losses": 148,
      "max_score": 76.8393903737067,
      "measured_at": null,
      "min_score": 55.133363671974216,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": 0.875,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 624,
      "rating_method": "sequential_elo",
      "raw_elo": 1728.0957648948586,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 66.45067157045091,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 407
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-6-sol:60281ce94ea88014",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 18
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.44844375,
        "mean": 0.352186484375,
        "median": 0.3360778125,
        "min": 0.30487875,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 18
        },
        "run_count": 17,
        "token_priced_attempt_count": 18,
        "total": 5.952425
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 62.05256256645749,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 258,
      "eligibility_flag": true,
      "entry_count": 16,
      "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": [
        "GB2-06"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.7777777777777778,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_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",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 8,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T05:21:14Z",
      "losses": 331,
      "max_score": 70.02605926216759,
      "measured_at": null,
      "min_score": 49.889474064355774,
      "model_code_failure_rate": 0.1111111111111111,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": 0.8888888888888888,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1418,
      "rating_method": "sequential_elo",
      "raw_elo": 1662.2072354663744,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": 1,
      "repaired_rate": 0.1111111111111111,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 60.252017078737964,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 829
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:x-ai-grok-4-5:9ade9c53df23b855",
      "capped_draws": 0,
      "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": 55.33875461534285,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "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-4.5",
        "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": 248,
      "max_score": 85.92138340901016,
      "measured_at": null,
      "min_score": 26.601192408895606,
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 840,
      "rating_method": "sequential_elo",
      "raw_elo": 1618.7643472205446,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 55.33875461534285,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 396
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:google-gemini-3-6-flash:157bc5e3bd81a2f8",
      "capped_draws": 0,
      "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": 56.609375270608496,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 479,
      "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": "2026-08-23T09:38:44Z",
      "losses": 457,
      "max_score": 89.86912515095916,
      "measured_at": null,
      "min_score": 16.214567763911244,
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1935,
      "rating_method": "sequential_elo",
      "raw_elo": 1646.8545969924107,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 54.750788157268985,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 999
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:google-gemini-3-5-flash:602942e58ad38e29",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "evidence_basis": "Provider-reported",
        "max": 0.5145615,
        "mean": 0.34875300000000004,
        "median": 0.335163,
        "min": 0.254883,
        "recorded_attempt_count": 19,
        "run_count": 8,
        "total": 2.790024
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 53.68699728666813,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 240,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": "2026-08-05T05:04:12Z",
      "losses": 193,
      "max_score": 86.87039539493097,
      "measured_at": null,
      "min_score": 25.159108940712393,
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 746,
      "rating_method": "sequential_elo",
      "raw_elo": 1602.1694011846157,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 8,
      "repaired_rate": 1.0,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 53.68699728666813,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 313
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-5:d75099c830e67381",
      "capped_draws": 0,
      "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": 51.90534748551461,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 261,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": 224,
      "max_score": 69.14142074882011,
      "measured_at": null,
      "min_score": 37.041752080817375,
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 786,
      "rating_method": "sequential_elo",
      "raw_elo": 1580.2794666999132,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 51.90534748551461,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 301
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-4:91029345b4b373cd",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 17
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.49506249999999996,
        "mean": 0.39100906250000006,
        "median": 0.40353625,
        "min": 0.253325,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 17
        },
        "run_count": 16,
        "token_priced_attempt_count": 17,
        "total": 6.256145
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 51.68213333592079,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 454,
      "eligibility_flag": true,
      "entry_count": 16,
      "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": 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": "2026-08-23T08:23:52Z",
      "losses": 376,
      "max_score": 83.97561557170286,
      "measured_at": null,
      "min_score": 22.354981368587474,
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1492,
      "rating_method": "sequential_elo",
      "raw_elo": 1599.0792267134148,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 51.68213333592079,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 662
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:meta-muse-spark-1-2:996fe7c6ac30c7b0",
      "capped_draws": 0,
      "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": 53.00511108061398,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 135,
      "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": "2026-08-23T02:44:09Z",
      "losses": 157,
      "max_score": 80.14955515143204,
      "measured_at": null,
      "min_score": 28.53778014221482,
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 601,
      "rating_method": "sequential_elo",
      "raw_elo": 1609.5375276472275,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 51.26485841178251,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 309
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-4-mini:84a1457658ce88c0",
      "capped_draws": 0,
      "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": 2.0151682500000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 46.84330020788533,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "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-5.4-mini",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": 251,
      "max_score": 59.73623054906832,
      "measured_at": null,
      "min_score": 21.626339283900553,
      "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": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 817,
      "rating_method": "sequential_elo",
      "raw_elo": 1534.3199012371015,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 46.84330020788533,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 315
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:moonshotai-kimi-k3:b25ef0843c2d972a",
      "capped_draws": 0,
      "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": 46.486279873467986,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 391,
      "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": "2026-08-22T07:54:09Z",
      "losses": 406,
      "max_score": 67.00524526280067,
      "measured_at": null,
      "min_score": 19.758668893473487,
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1225,
      "rating_method": "sequential_elo",
      "raw_elo": 1521.23164675783,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 46.486279873467986,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 428
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:claude-opus-4-8:7ef4979f6b3e9a70",
      "capped_draws": 0,
      "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": 1.7435250000000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 44.86814560751494,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 299,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": 204,
      "max_score": 75.46636108950283,
      "measured_at": null,
      "min_score": 16.344385607773184,
      "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": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 766,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.655158437621,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 44.86814560751494,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 263
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:o3:48e82ad54f426340",
      "capped_draws": 0,
      "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": 47.41858747665342,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 158,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": 225,
      "max_score": 59.630586714276724,
      "measured_at": null,
      "min_score": 35.65160344774605,
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 636,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.8636372392286,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 44.12796791753164,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 253
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:qwen-qwen3-7-plus:ea7926e26c1cc685",
      "capped_draws": 0,
      "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": 45.846013941307554,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 198,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": 218,
      "max_score": 70.50103787240695,
      "measured_at": null,
      "min_score": 23.250211486876427,
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 638,
      "rating_method": "sequential_elo",
      "raw_elo": 1534.6652906120871,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 42.664523344243406,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 222
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-6-terra:02f87be2a684b52a",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 11
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.24673750000000003,
        "mean": 0.16744,
        "median": 0.15809499999999999,
        "min": 0.108735,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 1.3395199999999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.525135923402324,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 290,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "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": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 8,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:18:32Z",
      "losses": 254,
      "max_score": 56.91665552510462,
      "measured_at": null,
      "min_score": 25.970772760443374,
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 794,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.3319203879903,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 42.525135923402324,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:z-ai-glm-5-2:f8720fd50b424f28",
      "capped_draws": 0,
      "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": 0.5271659940000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.11595469371872,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 234,
      "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": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": 164,
      "max_score": 65.44552694683463,
      "measured_at": null,
      "min_score": 19.008405115879473,
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 580,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.2147215764037,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 8,
      "repaired_rate": 1.0,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 42.11595469371872,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 182
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-6-luna:56b3e8082c8d4caf",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 18
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.009729675,
        "mean": 0.006791625,
        "median": 0.006426525,
        "min": 0.00488805,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 18
        },
        "run_count": 17,
        "token_priced_attempt_count": 18,
        "total": 0.11355404999999999
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 42.737047775268074,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 522,
      "eligibility_flag": true,
      "entry_count": 16,
      "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": [
        "GB2-06"
      ],
      "first_pass_admitted": 8,
      "first_pass_rate": 0.8888888888888888,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 8,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T09:38:55Z",
      "losses": 502,
      "max_score": 63.11042159913285,
      "measured_at": null,
      "min_score": 24.62525327826603,
      "model_code_failure_rate": 0.1111111111111111,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": 0.8888888888888888,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1478,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.2607166096343,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 41.496970083910846,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 454
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:moonshotai-kimi-k2-7-code:d430d8b81bf58172",
      "capped_draws": 0,
      "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": 44.40080151631661,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 184,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": 223,
      "max_score": 64.14078623679886,
      "measured_at": null,
      "min_score": 23.349084470138546,
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 648,
      "rating_method": "sequential_elo",
      "raw_elo": 1530.7330286175409,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 41.31960163911211,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 241
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:qwen-qwen3-7-max:a50a8f268d5fb73a",
      "capped_draws": 0,
      "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": 42.252226079601506,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 267,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": 247,
      "max_score": 72.79240290081826,
      "measured_at": null,
      "min_score": 15.965232157159793,
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 740,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.2408546796491,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 40.86500987157832,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 226
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:claude-sonnet-5:765bc291b12a711e",
      "capped_draws": 0,
      "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": 0.107477,
        "mean": 0.071838625,
        "median": 0.0695145,
        "min": 0.054787,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 17
        },
        "run_count": 16,
        "token_priced_attempt_count": 17,
        "total": 1.149418
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.78463603177035,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 450,
      "eligibility_flag": true,
      "entry_count": 15,
      "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": "2026-08-23T07:22:40Z",
      "losses": 484,
      "max_score": 50.64827352806712,
      "measured_at": null,
      "min_score": 25.215855476211686,
      "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": 1419,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.579727702851,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 40.78463603177035,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 485
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5:4164dfc523f2863c",
      "capped_draws": 0,
      "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": 1.4205012499999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.04137766611068,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 177,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": 255,
      "max_score": 59.51888474627783,
      "measured_at": null,
      "min_score": 22.173830070391556,
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 654,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.6960310752406,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 40.661083988892834,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 222
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-4-nano:33b97f3221951ed8",
      "capped_draws": 0,
      "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": 41.34035496936002,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 225,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": 495,
      "max_score": 61.40570645858217,
      "measured_at": null,
      "min_score": 13.75796311182292,
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1170,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.525156951902,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 38.47153521149206,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 450
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:x-ai-grok-build-0-1:40e9bde1c6eafc11",
      "capped_draws": 0,
      "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": 37.88184486713599,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 318,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": 294,
      "max_score": 63.41974151718129,
      "measured_at": null,
      "min_score": 21.669541208427077,
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 834,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.802017654402,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 37.88184486713599,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 222
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:openai-gpt-oss-120b:da344fed618b3552",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 16
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.00444719,
        "mean": 0.0024656575,
        "median": 0.002155255,
        "min": 0.0011302579999999999,
        "recorded_attempt_count": 16,
        "run_count": 8,
        "total": 0.019725259999999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 34.95147835537315,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 314,
      "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": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-07"
      ],
      "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": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:12:06Z",
      "losses": 240,
      "max_score": 44.324242271963605,
      "measured_at": null,
      "min_score": 21.805843612607568,
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 697,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.3086190207546,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 33.803958762497714,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 143
    },
    {
      "admitted_plugins": 26,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:stealth-ox-alpha:03024ebf053d776c",
      "capped_draws": 0,
      "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": 34.60521774334546,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 80,
      "eligibility_flag": true,
      "entry_count": 21,
      "evaluated_setting_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": "2026-08-23T14:12:11Z",
      "losses": 133,
      "max_score": 43.42288793742722,
      "measured_at": null,
      "min_score": 10.098703084006734,
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 308,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.884848536596,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 33.38909206008818,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:cohere-north-mini-code:b73629af9e588e3b",
      "capped_draws": 0,
      "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": 34.324135825057176,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 190,
      "eligibility_flag": true,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:19:01Z",
      "losses": 266,
      "max_score": 47.666905146048265,
      "measured_at": null,
      "min_score": 27.151591469186677,
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 642,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.1591263613343,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 31.942207583278662,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 14,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:deepseek-deepseek-v4-flash:ca5e50927e9f8fc5",
      "capped_draws": 0,
      "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": 0.05097333066
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 32.39306411364516,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 369,
      "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": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 431,
      "max_score": 47.63490899953319,
      "measured_at": null,
      "min_score": 16.923785423162606,
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1042,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.6237800519089,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 31.329541839544742,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 242
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:xiaomi-mimo-v2-5:f4cab288f8f1ec59",
      "capped_draws": 0,
      "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": 0.486187507
      },
      "codegen_evaluated_cells": 12,
      "conditional_success_score": 34.100059033206605,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 569,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": 590,
      "max_score": 41.01646733124801,
      "measured_at": null,
      "min_score": 22.281928770414922,
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1528,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.325095130375,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 30.812881665619475,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 369
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:meituan-longcat-2-0:26225fa06d2cccd9",
      "capped_draws": 0,
      "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": 31.99612108507919,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 436,
      "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": "2026-08-23T10:07:05Z",
      "losses": 894,
      "max_score": 44.134251044046394,
      "measured_at": null,
      "min_score": 19.174525876824212,
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1831,
      "rating_method": "sequential_elo",
      "raw_elo": 1388.0727613453926,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 29.775745754193835,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 501
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:nvidia-nemotron-3-ultra-550b-a55b:7859dde46c855271",
      "capped_draws": 0,
      "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": 34.21970648915008,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 186,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": 177,
      "max_score": 60.46921496514469,
      "measured_at": null,
      "min_score": 10.757672736091521,
      "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": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 486,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.5418005223535,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 29.54324213163337,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 6,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:google-gemini-3-1-flash-lite:036cd5692d58f681",
      "capped_draws": 0,
      "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": 0.081084
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 30.637348965354164,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 161,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": 328,
      "max_score": 42.15860784753806,
      "measured_at": null,
      "min_score": 0.5504962648416883,
      "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": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 650,
      "rating_method": "sequential_elo",
      "raw_elo": 1329.8076233730806,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 28.511265817165267,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 161
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:poolside-laguna-s-2-1:df6bf1faab8cda70",
      "capped_draws": 0,
      "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": 28.928846631529613,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 722,
      "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": "2026-08-23T03:23:43Z",
      "losses": 724,
      "max_score": 39.01837754189059,
      "measured_at": null,
      "min_score": 20.800006608149722,
      "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": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1759,
      "rating_method": "sequential_elo",
      "raw_elo": 1353.8771309681033,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 27.236248088672685,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 313
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:minimax-minimax-m3:f94aa3c94cf69a34",
      "capped_draws": 0,
      "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": 27.729849405690125,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 244,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": 350,
      "max_score": 45.82355270808264,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": 0.875,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 742,
      "rating_method": "sequential_elo",
      "raw_elo": 1339.0013490733593,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 26.819428816982096,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 148
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:google-gemini-3-5-flash-lite:ada8852a63812f17",
      "capped_draws": 0,
      "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": 27.137514209400695,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 713,
      "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": "2026-08-23T08:23:52Z",
      "losses": 1023,
      "max_score": 40.20117378359939,
      "measured_at": null,
      "min_score": 15.276461919221447,
      "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": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2116,
      "rating_method": "sequential_elo",
      "raw_elo": 1318.6580122995515,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 26.246541045387577,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 380
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:nex-agi-nex-n2-pro:bfccd9446404db2c",
      "capped_draws": 0,
      "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": 28.182587082918843,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 58,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": 307,
      "max_score": 42.524739590732,
      "measured_at": null,
      "min_score": 11.297346143143717,
      "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": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 492,
      "rating_method": "sequential_elo",
      "raw_elo": 1308.0891259112227,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 25.058257165591744,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 127
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:claude-opus-4-5:6145092901d96725",
      "capped_draws": 0,
      "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": 3.34216
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 50.773332684552884,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 347,
      "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-21T15:41:46Z",
      "losses": 421,
      "max_score": 82.15300774815739,
      "measured_at": null,
      "min_score": 22.143649514386354,
      "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": 1347,
      "rating_method": "sequential_elo",
      "raw_elo": 1567.107743213484,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 50.773332684552884,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 579
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:xiaomi-mimo-v2-5-pro:2437b68c7c28667e",
      "capped_draws": 0,
      "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": 44.414913787081844,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 128,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:11:01Z",
      "losses": 226,
      "max_score": 65.17750853680307,
      "measured_at": null,
      "min_score": 29.00219316035198,
      "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": 538,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.480717182855,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 41.332734586859196,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 184
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:qwen-qwen3-8-max:2315ff339b0c18d0",
      "capped_draws": 0,
      "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": 39.301499454569424,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 44,
      "eligibility_flag": false,
      "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T05:21:47Z",
      "losses": 41,
      "max_score": 53.968299220992186,
      "measured_at": null,
      "min_score": 11.78759779354171,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1526.3655621281669,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 39.301499454569424,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:google-gemma-4-31b-it:d0c0442b34151c5a",
      "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": 41.52733113500447,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 76,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [
        "GB2-01"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:57:18Z",
      "losses": 197,
      "max_score": 55.00038838965367,
      "measured_at": null,
      "min_score": 35.53416954938754,
      "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": 442,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.2316348393788,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 36.10559520111506,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 169
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:thinkingmachines-inkling-small:76482ff3d2fed50c",
      "capped_draws": 0,
      "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": 32.114071254168294,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 54,
      "eligibility_flag": false,
      "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T08:02:59Z",
      "losses": 62,
      "max_score": 45.96450843356181,
      "measured_at": null,
      "min_score": 14.155329190210882,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.2048683340781,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 31.182234699842784,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:stepfun-step-3-7-flash:efafeb77b13aa96b",
      "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": 36.456734403728596,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 153,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": 164,
      "max_score": 47.2576469157077,
      "measured_at": null,
      "min_score": 22.759457008176497,
      "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": 414,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.881190973985,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 30.656337271952143,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:thinkingmachines-inkling:3ab0a3aec8e194a6",
      "capped_draws": 0,
      "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": 1.2552692800000003
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 30.876311405534096,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 250,
      "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": "2026-08-22T12:49:16Z",
      "losses": 401,
      "max_score": 54.7905686677935,
      "measured_at": null,
      "min_score": 8.04764389452622,
      "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": 829,
      "rating_method": "sequential_elo",
      "raw_elo": 1337.094741645745,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 24.162019435171192,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 6,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:balanced:inclusionai-ling-3-0-flash:6f99584b1bad82dc",
      "capped_draws": 0,
      "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": 26.540316595936496,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 263,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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"
      ],
      "infra_excluded_game_aliases": [
        "GB2-05"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T10:20:46Z",
      "losses": 509,
      "max_score": 41.40501950685979,
      "measured_at": null,
      "min_score": 12.133934164094017,
      "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": 1004,
      "rating_method": "sequential_elo",
      "raw_elo": 1364.6434277050416,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 21.106736920958664,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 232
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:google-gemini-3-5-flash:602942e58ad38e29",
      "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": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T03:28:21Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1899.4210224251667,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 86.87039539493097,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 77
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 180,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-4:91029345b4b373cd",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 85,
      "draws": 19,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-08-19T23:51:30Z",
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1869.548743151603,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 83.87017034302815,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.015766029460877,
      "unilateral_faults": 2,
      "wins": 142
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01: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": 42,
      "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": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-20T01:48:05Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1832.923348449229,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 80.14955515143204,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:x-ai-grok-4-5:9ade9c53df23b855",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "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": "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": 21,
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1777.1699941075071,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 74.81649706686221,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 2,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:claude-fable-5:0d812a1d2c768408",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T18:12:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1746.9451046530367,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 71.4108605082153,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 2,
      "wins": 60
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 256,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:google-gemini-3-6-flash:157bc5e3bd81a2f8",
      "capped_draws": 97,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 111,
      "draws": 97,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 44,
      "max_score": null,
      "measured_at": "2026-08-22T09:26:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1726.9291590923472,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 70.09758000861065,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 115
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 210,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:claude-opus-5:f836f90d8fb9ff19",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 105,
      "draws": 19,
      "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": 64,
      "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": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1705.5104108029932,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 67.61473995183059,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.011966978180067,
      "unilateral_faults": 0,
      "wins": 127
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 145,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:moonshotai-kimi-k3:b25ef0843c2d972a",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "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": "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": 48,
      "max_score": null,
      "measured_at": "2026-08-20T02:13:25Z",
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1694.6446506662096,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 67.00524526280067,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 192,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-6-sol:60281ce94ea88014",
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 92,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 60,
      "max_score": null,
      "measured_at": "2026-08-22T19:57:46Z",
      "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": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1652.5834654247703,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 62.100714212737586,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.04972212351036,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-4-mini:84a1457658ce88c0",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T16:16:35Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1628.750407707507,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 59.73623054906832,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 2,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-5:d75099c830e67381",
      "capped_draws": 65,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 65,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:23:55Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1625.1613317167532,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 59.564351449683706,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 29
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 181,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-6-luna:56b3e8082c8d4caf",
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 88,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 68,
      "max_score": null,
      "measured_at": "2026-08-20T02:03:00Z",
      "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": 181,
      "rating_method": "sequential_elo",
      "raw_elo": 1617.5393757778043,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 58.43985564617407,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.521422675182308,
      "unilateral_faults": 0,
      "wins": 91
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 178,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:claude-opus-4-5:6145092901d96725",
      "capped_draws": 51,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 72,
      "draws": 51,
      "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": 43,
      "max_score": null,
      "measured_at": "2026-08-19T23:49:22Z",
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1593.5115898273448,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 57.216109384642444,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:nvidia-nemotron-3-ultra-550b-a55b:7859dde46c855271",
      "capped_draws": 20,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 20,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T02:39:09Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1528.1057891742366,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 49.52252542484147,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:qwen-qwen3-7-plus:ea7926e26c1cc685",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 18,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T09:57:34Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1513.515357215152,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 48.12999209690405,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:x-ai-grok-build-0-1:40e9bde1c6eafc11",
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "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": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T20:42:26Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.761287066289,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.273218336317015,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 42
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 187,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:claude-sonnet-5:765bc291b12a711e",
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 90,
      "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-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": 80,
      "max_score": null,
      "measured_at": "2026-08-19T22:40:40Z",
      "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": 187,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.6768021174773,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.075725762217715,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.728259216216795,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:claude-opus-4-8:7ef4979f6b3e9a70",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 17,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:21:46Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.264528764638,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.63359523406752,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:o3:48e82ad54f426340",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:22:08Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.681575830985,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.55826547626181,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-6-terra:02f87be2a684b52a",
      "capped_draws": 34,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 34,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:29:40Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.1014264525709,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.49963047361349,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 33
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 28,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:stealth-ox-alpha:03024ebf053d776c",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 14,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 10,
      "max_score": null,
      "measured_at": "2026-08-23T12:28:17Z",
      "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": 28,
      "rating_method": "sequential_elo",
      "raw_elo": 1530.420159897876,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.42288793742722,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 85.34944487358055,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:moonshotai-kimi-k2-7-code:d430d8b81bf58172",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:23:03Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.399910028884,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 42.57288379544755,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:qwen-qwen3-8-max:2315ff339b0c18d0",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 10,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 4,
      "max_score": null,
      "measured_at": "2026-08-22T16:31:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.3453591301432,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.01649081370751,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:google-gemini-3-1-flash-lite:036cd5692d58f681",
      "capped_draws": 44,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 44,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:21:14Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.0722052107417,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.98668493442913,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 22
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 366,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:google-gemini-3-5-flash-lite:ada8852a63812f17",
      "capped_draws": 73,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 142,
      "draws": 73,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 155,
      "max_score": null,
      "measured_at": "2026-08-22T19:58:37Z",
      "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": 366,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.2662451167348,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.20117378359939,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 138
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:z-ai-glm-5-2:f8720fd50b424f28",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "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": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T01:08:24Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.7540280999642,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.0036272413998,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 160,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:poolside-laguna-s-2-1:df6bf1faab8cda70",
      "capped_draws": 28,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 28,
      "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": 74,
      "max_score": null,
      "measured_at": "2026-08-22T19:58:37Z",
      "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": 160,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.0856930075604,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.01837754189059,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:openai-gpt-oss-120b:da344fed618b3552",
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 24,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:12:06Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.8019145344933,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.83660567477785,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:thinkingmachines-inkling:3ab0a3aec8e194a6",
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "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": "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": 76,
      "max_score": null,
      "measured_at": "2026-08-15T02:21:14Z",
      "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": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.3433979275337,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 33.14168798272348,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 152,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:deepseek-deepseek-v4-flash:ca5e50927e9f8fc5",
      "capped_draws": 39,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 76,
      "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": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 82,
      "max_score": null,
      "measured_at": "2026-07-31T02:23:17Z",
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1360.8578517467413,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.116626000567756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 31
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 212,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:xiaomi-mimo-v2-5:f4cab288f8f1ec59",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 98,
      "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": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:23:13Z",
      "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": 212,
      "rating_method": "sequential_elo",
      "raw_elo": 1343.1444354252926,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.023169583821865,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 4.612181847919805,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:thinkingmachines-inkling-small:76482ff3d2fed50c",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "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": "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": 15,
      "max_score": null,
      "measured_at": "2026-08-22T09:26:27Z",
      "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": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1346.7122318417303,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.47208042284504,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:minimax-minimax-m3:f94aa3c94cf69a34",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:21:31Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1293.2880278495784,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 25.911126435305174,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5:4164dfc523f2863c",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:11:21Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1257.9362460272719,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 22.173830070391556,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:inclusionai-ling-3-0-flash:6f99584b1bad82dc",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 15,
      "draws": 34,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 107,
      "max_score": null,
      "measured_at": "2026-08-20T01:50:48Z",
      "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": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1249.214707380887,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.956639805537932,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 24.068787932399015,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:qwen-qwen3-7-max:a50a8f268d5fb73a",
      "capped_draws": 30,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 30,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:11:20Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1196.0815382797539,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 15.965232157159793,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 190,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-4-nano:33b97f3221951ed8",
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 92,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:22:02Z",
      "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": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1175.0071677189458,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 13.75796311182292,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.9734349083065625,
      "unilateral_faults": 2,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:claude-fable-5:0d812a1d2c768408",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 31,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T02:44:38Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1685.6539281264988,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 68.84186917568367,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 2,
      "wins": 38
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 152,
      "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": 76,
      "draws": 68,
      "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": 16,
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1652.4738991796207,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 61.26562064904274,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 68
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 146,
      "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": 2,
      "distinct_rated_opponents": 69,
      "draws": 79,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-08-22T14:35:05Z",
      "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": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1602.7750164385534,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 49.889474064355774,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:gpt-5-5:d75099c830e67381",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 45,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T09:39:04Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1576.1121672722809,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.99378748372811,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 67,
      "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": 31,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 6,
      "max_score": null,
      "measured_at": "2026-08-19T23:36:40Z",
      "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": 67,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.5573026507243,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 28.53778014221482,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.883906259083243,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "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": 49,
      "draws": 69,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "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": 16,
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.6220047983245,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.601192408895606,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:gpt-5-6-terra:02f87be2a684b52a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 76,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T10:43:21Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.4957620772557,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 25.970772760443374,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:google-gemini-3-5-flash:602942e58ad38e29",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "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": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T01:05:13Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.007826929545,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 25.82657411049858,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 140,
      "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": 2,
      "distinct_rated_opponents": 66,
      "draws": 128,
      "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": 7,
      "max_score": null,
      "measured_at": "2026-08-15T01:46:36Z",
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.9466411620278,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 25.215855476211686,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 15.8742369405862,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 138,
      "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": 2,
      "distinct_rated_opponents": 66,
      "draws": 129,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-23T06:52:36Z",
      "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": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.457570126053,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 24.62525327826603,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.05264788810895,
      "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: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": 41,
      "draws": 101,
      "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": 3,
      "max_score": null,
      "measured_at": "2026-08-15T01:43:34Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.8316916886058,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 23.401496235109175,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:moonshotai-kimi-k2-7-code:d430d8b81bf58172",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 91,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:15:10Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.596618403244,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 23.349084470138546,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:qwen-qwen3-7-plus:ea7926e26c1cc685",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 81,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:15:15Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.3725891120614,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 23.250211486876427,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:stepfun-step-3-7-flash:efafeb77b13aa96b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "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": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T09:30:46Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.1857236712685,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 22.759457008176497,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 107,
      "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": 41,
      "draws": 105,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 2,
      "max_score": null,
      "measured_at": "2026-08-22T08:45:19Z",
      "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": 107,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.044979547752,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 22.367578645782174,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 4.362522432468809,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 159,
      "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": 2,
      "distinct_rated_opponents": 74,
      "draws": 138,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-08-19T21:54:48Z",
      "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": 159,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.0972191858511,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 22.354981368587474,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.997990851037477,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:xiaomi-mimo-v2-5:f4cab288f8f1ec59",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 119,
      "draws": 228,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T04:42:24Z",
      "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": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.0985457153822,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 22.281928770414922,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.90656379732316,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 138,
      "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": 54,
      "draws": 125,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-08-19T21:55:39Z",
      "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": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.4846616121374,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 22.143649514386354,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:gpt-5-4-nano:33b97f3221951ed8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 77,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:15:35Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.7131921870432,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 21.854529388279282,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:openai-gpt-oss-120b:da344fed618b3552",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 77,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:15:41Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.9362990217546,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 21.805843612607568,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:x-ai-grok-build-0-1:40e9bde1c6eafc11",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 86,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:16:24Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.922484272434,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 21.669541208427077,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:gpt-5-4-mini:84a1457658ce88c0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 84,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:16:41Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.1832965878284,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 21.626339283900553,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2,
      "attempted_matches": 236,
      "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": 85,
      "draws": 225,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 9,
      "max_score": null,
      "measured_at": "2026-08-23T03:23:43Z",
      "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": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.1384095012668,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 21.191551614417335,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.279970601756496,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:qwen-qwen3-7-max:a50a8f268d5fb73a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 83,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T03:19:01Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.125463708624,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.847233163024622,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 39,
      "draws": 79,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 18,
      "max_score": null,
      "measured_at": "2026-08-22T07:54:09Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.9653251764248,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.758668893473487,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:z-ai-glm-5-2:f8720fd50b424f28",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "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": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.1999436475344,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.008405115879473,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:nvidia-nemotron-3-ultra-550b-a55b:7859dde46c855271",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "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": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T04:41:42Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.1606606288503,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 17.357469503708607,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 136,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:deepseek-deepseek-v4-flash:ca5e50927e9f8fc5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 68,
      "draws": 114,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 20,
      "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": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.4662368310856,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 16.923785423162606,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.461902543922633,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:claude-opus-4-8:7ef4979f6b3e9a70",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 72,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T05:47:14Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.7183503047993,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 16.344385607773184,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "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": 44,
      "draws": 82,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.5362643626052,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 16.214567763911244,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "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": 11,
      "draws": 20,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 0,
      "max_score": null,
      "measured_at": "2026-08-23T00:33:40Z",
      "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": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.2472717904682,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 14.155329190210882,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 22,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:inclusionai-ling-3-0-flash:6f99584b1bad82dc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 11,
      "draws": 98,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 22,
      "max_score": null,
      "measured_at": "2026-08-19T21:57:09Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.556144588857,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 12.133934164094017,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 33.25453326951843,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "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": 10,
      "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": "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": 2,
      "max_score": null,
      "measured_at": "2026-08-20T05:43:08Z",
      "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": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.6963543985923,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 11.78759779354171,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:minimax-minimax-m3:f94aa3c94cf69a34",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T08:16:45Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.2739821056432,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 11.783172968660383,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 42,
      "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": 21,
      "draws": 24,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 11,
      "max_score": null,
      "measured_at": "2026-08-23T14:09:45Z",
      "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": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.162820902962,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 10.098703084006734,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 162,
      "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": 81,
      "draws": 8,
      "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": 15,
      "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": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1867.8291510173494,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 95.92764370282903,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.468842775200363,
      "unilateral_faults": 0,
      "wins": 139
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:moonshotai-kimi-k3:b25ef0843c2d972a",
      "capped_draws": 3,
      "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": "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": 21,
      "max_score": null,
      "measured_at": "2026-08-21T11:42:46Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1644.1494064849203,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 66.78378455408968,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5-6-sol:60281ce94ea88014",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 72,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 41,
      "max_score": null,
      "measured_at": "2026-08-21T15:52:22Z",
      "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": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1599.4922084182406,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 59.04540587223423,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 14.466340901271955,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:google-gemini-3-5-flash:602942e58ad38e29",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:19:33Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1577.6092570519809,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 55.84887374161656,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:thinkingmachines-inkling:3ab0a3aec8e194a6",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "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": "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": 37,
      "max_score": null,
      "measured_at": "2026-08-22T12:02:27Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.1129209687915,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.7905686677935,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:meta-muse-spark-1-2:996fe7c6ac30c7b0",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "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": "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": 30,
      "max_score": null,
      "measured_at": "2026-08-21T11:43:18Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.3955110326083,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.70215835783597,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:deepseek-deepseek-v4-flash:ca5e50927e9f8fc5",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "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": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 21,
      "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": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.0961019109775,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 47.63490899953319,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 160,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:claude-opus-4-5:6145092901d96725",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 77,
      "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": 48,
      "max_score": null,
      "measured_at": "2026-08-21T04:34:57Z",
      "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": 160,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.8789320043286,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 47.38893238646811,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 270,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:google-gemini-3-6-flash:157bc5e3bd81a2f8",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 106,
      "draws": 69,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 113,
      "max_score": null,
      "measured_at": "2026-08-22T11:01:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 270,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.3603963409328,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.93983383805609,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "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": 39,
      "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": "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": 26,
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.9890080189186,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.92997006877206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 142,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:meituan-longcat-2-0:26225fa06d2cccd9",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "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": "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": 39,
      "max_score": null,
      "measured_at": "2026-08-21T09:13:52Z",
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.9131306078064,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.134251044046394,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 85,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5-4-mini:84a1457658ce88c0",
      "capped_draws": 12,
      "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": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T06:55:18Z",
      "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": 85,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.1394784776523,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.25460249709266,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.16638660171921,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5-6-terra:02f87be2a684b52a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "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-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:19:59Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.6473394621028,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.06898280210667,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 14
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 25,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:stealth-ox-alpha:03024ebf053d776c",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 12,
      "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": "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": 6,
      "max_score": null,
      "measured_at": "2026-08-23T14:10:38Z",
      "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": 24,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.4080832752197,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.818965805599504,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 94.92504905630729,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 17,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03: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": 9,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 5,
      "max_score": null,
      "measured_at": "2026-08-21T15:54:27Z",
      "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": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.8258524700977,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.330911797900164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 74.10113019775793,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:claude-sonnet-5:765bc291b12a711e",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 31,
      "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": 36,
      "max_score": null,
      "measured_at": "2026-08-22T14:30:42Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.2008449551374,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.02092072410418,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 167,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5-6-luna:56b3e8082c8d4caf",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 79,
      "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-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": 61,
      "max_score": null,
      "measured_at": "2026-08-23T05:19:28Z",
      "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": 167,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.8197120792142,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.31631498921994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.90304461595112,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 176,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5-4:91029345b4b373cd",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 83,
      "draws": 86,
      "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": 51,
      "max_score": null,
      "measured_at": "2026-08-23T08:23:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.0849528487836,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.977818353684654,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.340523799551441,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "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": 9,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 5,
      "max_score": null,
      "measured_at": "2026-08-23T02:31:42Z",
      "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": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.4910334028175,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.823095003355,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 281,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:google-gemini-3-5-flash-lite:ada8852a63812f17",
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 103,
      "draws": 119,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 109,
      "max_score": null,
      "measured_at": "2026-08-23T08:23:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 281,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.9985313839934,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.12765176299469,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:claude-opus-4-8:7ef4979f6b3e9a70",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "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-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T10:31:14Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.7477631553459,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.68653930194108,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5-5:d75099c830e67381",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "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-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T11:59:49Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.9850240219848,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.041752080817375,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:z-ai-glm-5-2:f8720fd50b424f28",
      "capped_draws": 15,
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T02:57:05Z",
      "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": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.1124041249502,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.602494823476015,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 318,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:poolside-laguna-s-2-1:df6bf1faab8cda70",
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 117,
      "draws": 133,
      "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": 123,
      "max_score": null,
      "measured_at": "2026-08-23T03:05:15Z",
      "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": 318,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.9195777629861,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.84632546230651,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:nex-agi-nex-n2-pro:bfccd9446404db2c",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 35,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T08:55:37Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.8192171011551,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.022102828158765,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:x-ai-grok-build-0-1:40e9bde1c6eafc11",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "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": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:01:44Z",
      "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": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.5993597267618,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 33.32639046166839,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:openai-gpt-oss-120b:da344fed618b3552",
      "capped_draws": 8,
      "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:30:48Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.558557661116,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.858125032877226,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5:4164dfc523f2863c",
      "capped_draws": 1,
      "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": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:53:39Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.0902606081052,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.739075020104682,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 32,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:cohere-north-mini-code:b73629af9e588e3b",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 16,
      "draws": 28,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 24,
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.0627821631542,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.765006071781528,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 44.67073949561819,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 2,
      "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": 2,
      "distinct_rated_opponents": 88,
      "draws": 97,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-08-22T06:40:40Z",
      "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": 186,
      "rating_method": "sequential_elo",
      "raw_elo": 1663.9931662036106,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 68.03330219031832,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.322854653679386,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:claude-fable-5:0d812a1d2c768408",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 33,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:23:59Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1582.2001981056562,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 55.133363671974216,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:xiaomi-mimo-v2-5-pro:2437b68c7c28667e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 51,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:11:01Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1566.3530638646457,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 53.300611514890754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5-4-nano:33b97f3221951ed8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 64,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:04:11Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1562.2888242629197,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.743625903198904,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 25
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 206,
      "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": 103,
      "draws": 90,
      "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": 57,
      "max_score": null,
      "measured_at": "2026-08-05T05:03:35Z",
      "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": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.023551151262,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.394609038466754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.280733777820661,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5-4-mini:84a1457658ce88c0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 61,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:11:05Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.7577793037303,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.09375303448146,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:google-gemini-3-5-flash:602942e58ad38e29",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:04:12Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.5455372468282,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 51.31859933665385,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:stepfun-step-3-7-flash:efafeb77b13aa96b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "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": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:11:10Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.32655258939,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.03853672066733,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5-6-terra:02f87be2a684b52a",
      "capped_draws": 0,
      "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": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:15:06Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.6341572765252,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.865298973012386,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:google-gemini-3-1-flash-lite:036cd5692d58f681",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 77,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T03:46:58Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.6174746882057,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 42.15860784753806,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 2,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:qwen-qwen3-7-max:a50a8f268d5fb73a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 66,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:03:39Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.791657928284,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 42.07260490289768,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 137,
      "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": 53,
      "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": "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": 17,
      "max_score": null,
      "measured_at": "2026-08-22T06:51:00Z",
      "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": 133,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.9182974099629,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.65185972817385,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5:4164dfc523f2863c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 62,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:03:31Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.6589592065263,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.81207563674785,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:minimax-minimax-m3:f94aa3c94cf69a34",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 76,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:04:06Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.269501274785,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.496965218840195,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 110,
      "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": 54,
      "draws": 82,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 16,
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.3694583369315,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.43774279100727,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:z-ai-glm-5-2:f8720fd50b424f28",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T02:38:28Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.7254504864673,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.35454880564338,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:x-ai-grok-build-0-1:40e9bde1c6eafc11",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 84,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:57:28Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.7467967975713,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.244014723647986,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 104,
      "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": 51,
      "draws": 76,
      "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": 16,
      "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": 103,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.6181811749257,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.978937009585955,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.279033784546012,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5-5:d75099c830e67381",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 63,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:28:39Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.5304118625747,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.63154205082826,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 22
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 178,
      "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": 2,
      "distinct_rated_opponents": 85,
      "draws": 118,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-22T11:33:38Z",
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.9729843342425,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.38095957381465,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.373376069016812,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:claude-opus-4-8:7ef4979f6b3e9a70",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 87,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:15:12Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.653364825019,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.94522426719343,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 253,
      "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": 111,
      "draws": 195,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-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": 31,
      "max_score": null,
      "measured_at": "2026-08-22T14:13:36Z",
      "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": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.3565254548685,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.573622197421955,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.7477795630767012,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 176,
      "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": 2,
      "distinct_rated_opponents": 83,
      "draws": 145,
      "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": 16,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:21Z",
      "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": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.374112829179,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.358671625552,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.5031429046309,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 292,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:xiaomi-mimo-v2-5:f4cab288f8f1ec59",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 134,
      "draws": 219,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T11:50:25Z",
      "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": 292,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.8146522742954,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.845925647546906,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.756124848353349,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:deepseek-deepseek-v4-flash:ca5e50927e9f8fc5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "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": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 9,
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.9778216962018,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.49517602497302,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:google-gemma-4-31b-it:d0c0442b34151c5a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "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": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T02:50:00Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.0389711785886,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.342280705591044,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 2,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "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": 46,
      "draws": 94,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 19,
      "max_score": null,
      "measured_at": "2026-08-22T11:33:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.3921381611772,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.872662603409985,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 255,
      "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": 114,
      "draws": 188,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 37,
      "max_score": null,
      "measured_at": "2026-08-21T20:33:16Z",
      "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": 255,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.1461491938412,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.37827885826509,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.042462425705284,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:openai-gpt-oss-120b:da344fed618b3552",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 83,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:14:37Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.7004190221962,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.96640446666731,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:o3:48e82ad54f426340",
      "capped_draws": 0,
      "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": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T11:49:23Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.4224780953568,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.65160344774605,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 184,
      "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": 2,
      "distinct_rated_opponents": 86,
      "draws": 107,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-08-22T04:21:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.5740560255051,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.482620682862695,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.324296951529915,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "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": 24,
      "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": "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": 9,
      "max_score": null,
      "measured_at": "2026-08-23T12:27:48Z",
      "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": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.2014764650874,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.0666411169392,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:cohere-north-mini-code:b73629af9e588e3b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 32,
      "draws": 81,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 18,
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.3736279368563,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 33.52310753913016,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 25.383326230453278,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:moonshotai-kimi-k2-7-code:d430d8b81bf58172",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 79,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:17:06Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.1215027312614,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.85833209398961,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:inclusionai-ling-3-0-flash:6f99584b1bad82dc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 25,
      "draws": 129,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 27,
      "max_score": null,
      "measured_at": "2026-08-22T04:21:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.6985624189183,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.370699474354865,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.984274827972971,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "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": 10,
      "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": "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": 5,
      "max_score": null,
      "measured_at": "2026-08-23T08:02:59Z",
      "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": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.3700914144779,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.39027464270986,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "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": 8,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-21T20:10:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.637623633983,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.86262516391439,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "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": 36,
      "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": "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": 27,
      "max_score": null,
      "measured_at": "2026-08-22T06:20:10Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.1381799035316,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 28.86928741865205,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 152,
      "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": 59,
      "draws": 94,
      "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": 46,
      "max_score": null,
      "measured_at": "2026-08-22T06:20:20Z",
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1380.6694525948496,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.24251380391939,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 285,
      "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": 106,
      "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": "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": 90,
      "max_score": null,
      "measured_at": "2026-08-23T06:52:50Z",
      "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": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1336.8963911626097,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.174525876824212,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.8522727272727293,
      "unilateral_faults": 23,
      "wins": 19
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 226,
      "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": 113,
      "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": 28,
      "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": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1925.6591942822074,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 83.24150998152905,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.0806419155977727,
      "unilateral_faults": 0,
      "wins": 198
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 324,
      "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": 132,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 82,
      "max_score": null,
      "measured_at": "2026-08-23T02:44:09Z",
      "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": 324,
      "rating_method": "sequential_elo",
      "raw_elo": 1770.0664811162064,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 70.83047446085692,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 242
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 192,
      "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": 2,
      "distinct_rated_opponents": 93,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 54,
      "max_score": null,
      "measured_at": "2026-08-22T11:11:03Z",
      "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": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1743.0258196719778,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 67.8135861604195,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.025404183609156,
      "unilateral_faults": 0,
      "wins": 138
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5-5:d75099c830e67381",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:43:10Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1717.6614023179375,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 65.742104336769,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:x-ai-grok-build-0-1:40e9bde1c6eafc11",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:34:43Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1685.2701621628198,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 63.41974151718129,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:claude-fable-5:0d812a1d2c768408",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:01:05Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1679.6354629058385,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 62.71165398791373,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "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": 58,
      "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": 46,
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1660.642134309636,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 61.274740553352146,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 70
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 216,
      "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": 2,
      "distinct_rated_opponents": 104,
      "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": 87,
      "max_score": null,
      "measured_at": "2026-08-20T05:43:22Z",
      "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": 216,
      "rating_method": "sequential_elo",
      "raw_elo": 1652.5584228156804,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 60.47818486339551,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 4.360926855613204,
      "unilateral_faults": 0,
      "wins": 129
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:qwen-qwen3-7-plus:ea7926e26c1cc685",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:48:47Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1607.3794802947366,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 56.95170350971318,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5-6-terra:02f87be2a684b52a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:41:58Z",
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1609.1466507381233,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 56.91665552510462,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5:4164dfc523f2863c",
      "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:41:12Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1607.1651624106053,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 56.63196638824444,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:moonshotai-kimi-k2-7-code:d430d8b81bf58172",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:26:21Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1601.2213719654865,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 56.229748233144726,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:google-gemma-4-31b-it:d0c0442b34151c5a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:57:18Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1583.880968834933,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 55.00038838965367,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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:GB2-05:publication-row.v1:balanced:gpt-5-4-mini:84a1457658ce88c0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:08:36Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1576.1336146218378,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.357048515026754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 74
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 200,
      "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": 75,
      "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": 91,
      "max_score": null,
      "measured_at": "2026-08-20T05:12:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1557.6899839620967,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 53.45354337379487,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:z-ai-glm-5-2:f8720fd50b424f28",
      "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": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T00:59:23Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1563.1378187943271,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.64602705866004,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:google-gemini-3-5-flash:602942e58ad38e29",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:42:51Z",
      "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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1553.2266000489765,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.301082285856566,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 176,
      "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": 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": "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": 70,
      "max_score": null,
      "measured_at": "2026-08-20T12:14:57Z",
      "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": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1544.3586605576277,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.19271965091757,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 94,
      "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": 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": "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": 41,
      "max_score": null,
      "measured_at": "2026-08-23T02:44:09Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1554.8886887946508,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.15591097203426,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:qwen-qwen3-7-max:a50a8f268d5fb73a",
      "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": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:00:43Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1544.3386733865298,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 51.71679831534971,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:claude-opus-4-8:7ef4979f6b3e9a70",
      "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": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:49:27Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.859169314774,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 51.154684162643335,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 66
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 209,
      "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": 2,
      "distinct_rated_opponents": 102,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 108,
      "max_score": null,
      "measured_at": "2026-08-22T11:01:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 209,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.8552682209965,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.81791174484506,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.148039332521046,
      "unilateral_faults": 0,
      "wins": 101
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 208,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5-4-nano:33b97f3221951ed8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 103,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:42:37Z",
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.204965591142,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.75472568681504,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.286300544311842,
      "unilateral_faults": 0,
      "wins": 112
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 196,
      "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": 2,
      "distinct_rated_opponents": 94,
      "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": 82,
      "max_score": null,
      "measured_at": "2026-08-23T07:22:40Z",
      "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": 1535.9510213460148,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.64827352806712,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.571294191973962,
      "unilateral_faults": 0,
      "wins": 114
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "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": 11,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:47Z",
      "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": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1577.631160970109,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.2040113856351,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:o3:48e82ad54f426340",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:51:41Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.8097339730377,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 48.39087874034282,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:cohere-north-mini-code:b73629af9e588e3b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "cohere/north-mini-code",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 56,
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.9170144593968,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 47.666905146048265,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 20.157312871896224,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:stepfun-step-3-7-flash:efafeb77b13aa96b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:51:39Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.530653934251,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 47.2576469157077,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1,
      "attempted_matches": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:openai-gpt-oss-120b:da344fed618b3552",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:10:14Z",
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.517503684909,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.324242271963605,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 49
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 342,
      "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": 125,
      "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": 190,
      "max_score": null,
      "measured_at": "2026-08-22T11:34:23Z",
      "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": 342,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.4395331894639,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.53426134564661,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 152
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:xiaomi-mimo-v2-5:f4cab288f8f1ec59",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 120,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T22:17:40Z",
      "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": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.8281286887423,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.01646733124801,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.4376202060078436,
      "unilateral_faults": 0,
      "wins": 104
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "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": 24,
      "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": 34,
      "max_score": null,
      "measured_at": "2026-08-23T14:12:11Z",
      "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": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.7474591280127,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.866899596586855,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 375,
      "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": 138,
      "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": 252,
      "max_score": null,
      "measured_at": "2026-08-22T14:35:15Z",
      "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": 375,
      "rating_method": "sequential_elo",
      "raw_elo": 1299.0500309172046,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.896275052743633,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 123
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "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": 8,
      "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": 12,
      "max_score": null,
      "measured_at": "2026-08-20T12:25:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1363.5335221414252,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.61761768988316,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:xiaomi-mimo-v2-5-pro:2437b68c7c28667e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:42:02Z",
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1293.3384425319216,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.691959004825147,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:nex-agi-nex-n2-pro:bfccd9446404db2c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T09:17:51Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1281.5487586993647,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.654555612064655,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 32
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 158,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:deepseek-deepseek-v4-flash:ca5e50927e9f8fc5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 79,
      "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": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 93,
      "max_score": null,
      "measured_at": "2026-07-31T03:33:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1284.9171506996952,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.431499631947965,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 12.154975300928378,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 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",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:51:41Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1241.8551704733636,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.598584601571144,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:google-gemini-3-1-flash-lite:036cd5692d58f681",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T21:09:30Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1196.77816581129,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 22.487988563537684,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 28
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 326,
      "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": 123,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 259,
      "max_score": null,
      "measured_at": "2026-08-22T12:02:21Z",
      "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": 326,
      "rating_method": "sequential_elo",
      "raw_elo": 1115.6686528221212,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 16.497222114125087,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:minimax-minimax-m3:f94aa3c94cf69a34",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T23:59:53Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 924.4368254590598,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 308,
      "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": 121,
      "draws": 21,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 21,
      "max_score": null,
      "measured_at": "2026-08-23T09:38:44Z",
      "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": 308,
      "rating_method": "sequential_elo",
      "raw_elo": 1956.8985581879415,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 89.86912515095916,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 266
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 174,
      "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": 2,
      "distinct_rated_opponents": 83,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-22T11:41:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1899.3144706102646,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 83.97561557170286,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.614857365683216,
      "unilateral_faults": 0,
      "wins": 149
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:google-gemini-3-5-flash:602942e58ad38e29",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:16:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1868.3321704609657,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 81.27954496028467,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:claude-fable-5:0d812a1d2c768408",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "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-fable-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T10:57:46Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1815.5838157198623,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 76.8393903737067,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:claude-opus-4-8:7ef4979f6b3e9a70",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T08:42:55Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1799.7073501929144,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 75.46636108950283,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:qwen-qwen3-7-plus:ea7926e26c1cc685",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 5,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T07:40:51Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1740.616275075024,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 70.50103787240695,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:z-ai-glm-5-2:f8720fd50b424f28",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-30T23:51:19Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1689.1739025328532,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 65.44552694683463,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:xiaomi-mimo-v2-5-pro:2437b68c7c28667e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T05:25:24Z",
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1677.2246416402638,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 65.17750853680307,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 190,
      "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": 73,
      "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": "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": 74,
      "max_score": null,
      "measured_at": "2026-08-20T21:54:25Z",
      "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": 190,
      "rating_method": "sequential_elo",
      "raw_elo": 1661.6059928496998,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 64.6071323338313,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 2,
      "attempted_matches": 200,
      "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": 2,
      "distinct_rated_opponents": 95,
      "draws": 11,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-08-22T22:29:24Z",
      "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": 199,
      "rating_method": "sequential_elo",
      "raw_elo": 1655.3643700867465,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 63.11042159913285,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.259958887663135,
      "unilateral_faults": 1,
      "wins": 122
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 214,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5-4-nano:33b97f3221951ed8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 106,
      "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-5.4-nano",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T06:55:07Z",
      "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": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1634.145784366343,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 61.40570645858217,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 4.376451717525809,
      "unilateral_faults": 0,
      "wins": 122
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:nvidia-nemotron-3-ultra-550b-a55b:7859dde46c855271",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:41:43Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1625.0173972189637,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 60.46921496514469,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:o3:48e82ad54f426340",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 11,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:57:23Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1597.6476744413671,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 58.234720321902785,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:qwen-qwen3-7-max:a50a8f268d5fb73a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 12,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:35:11Z",
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1579.5531911998273,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 56.73068128436687,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5:4164dfc523f2863c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 7,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:03:53Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1580.3019624316037,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 56.70292816921177,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 55
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 184,
      "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": 2,
      "distinct_rated_opponents": 88,
      "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-5.6-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": 69,
      "max_score": null,
      "measured_at": "2026-08-23T00:03:03Z",
      "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": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1571.4134191801722,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 55.7230339519561,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 102
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5-4-mini:84a1457658ce88c0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:53:50Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.2793243998406,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.94736966606298,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "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": 10,
      "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": "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": 6,
      "max_score": null,
      "measured_at": "2026-08-22T11:01:36Z",
      "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": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1596.932346317202,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 53.968299220992186,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 196,
      "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": 71,
      "draws": 16,
      "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": 82,
      "max_score": null,
      "measured_at": "2026-08-20T18:11:58Z",
      "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": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.9782452617544,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.754127680852754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5-6-terra:02f87be2a684b52a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:57:28Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.2749957494511,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 49.922377861903456,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5-5:d75099c830e67381",
      "capped_draws": 0,
      "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T09:49:28Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.311575824817,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 47.27455398323267,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "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": 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": "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": 62,
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.9671489840152,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.169198045990534,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 52
    },
    {
      "admitted_plugins": 2,
      "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": 2,
      "distinct_rated_opponents": 103,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-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": 112,
      "max_score": null,
      "measured_at": "2026-08-22T17:46:09Z",
      "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": 1436.5416474435287,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.29917985650991,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 4.626731529401584,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:x-ai-grok-build-0-1:40e9bde1c6eafc11",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:10:00Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.0192370849595,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.0367051388074,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:google-gemini-3-1-flash-lite:036cd5692d58f681",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T10:58:16Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1399.0006395624505,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.39995376105174,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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:GB2-06:publication-row.v1:balanced:minimax-minimax-m3:f94aa3c94cf69a34",
      "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": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:46:15Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1342.8613766220567,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.399691312701414,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:xiaomi-mimo-v2-5:f4cab288f8f1ec59",
      "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": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:57:10Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1340.4538958273813,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.242213374439,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 121,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:openai-gpt-oss-120b:da344fed618b3552",
      "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": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T20:06:27Z",
      "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": 121,
      "rating_method": "sequential_elo",
      "raw_elo": 1340.0030877685297,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.16541568514887,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 42
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 28,
      "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": 14,
      "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": "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": 22,
      "max_score": null,
      "measured_at": "2026-08-23T12:15:59Z",
      "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": 28,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.7352199144916,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.79067812355425,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 85.34944487358055,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:google-gemma-4-31b-it:d0c0442b34151c5a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T13:20:46Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1333.1575713568993,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.53416954938754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 19,
      "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": 9,
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-23T04:48:33Z",
      "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": 19,
      "rating_method": "sequential_elo",
      "raw_elo": 1377.382181449011,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.79473339617072,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 68.05339887498948,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 346,
      "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": 131,
      "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": "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": 227,
      "max_score": null,
      "measured_at": "2026-08-22T19:42:16Z",
      "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": 346,
      "rating_method": "sequential_elo",
      "raw_elo": 1266.7108166706953,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.33372549288365,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 96
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:stepfun-step-3-7-flash:efafeb77b13aa96b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T23:37:39Z",
      "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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1267.48183370103,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.77129697036285,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:cohere-north-mini-code:b73629af9e588e3b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 35,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 79,
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1268.3538600217935,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 28.469827580005035,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 23.187341079842824,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 160,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:deepseek-deepseek-v4-flash:ca5e50927e9f8fc5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 80,
      "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": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 101,
      "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": 160,
      "rating_method": "sequential_elo",
      "raw_elo": 1244.2632602994895,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 27.173879247378046,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 52,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:inclusionai-ling-3-0-flash:6f99584b1bad82dc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 26,
      "draws": 2,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 137,
      "max_score": null,
      "measured_at": "2026-08-22T10:20:46Z",
      "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": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1240.7179893577259,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.835290028835875,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 12.465140987172258,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:nex-agi-nex-n2-pro:bfccd9446404db2c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "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": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:35:20Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1195.0146527344775,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 23.41419124049507,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 176,
      "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": 66,
      "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": "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": 125,
      "max_score": null,
      "measured_at": "2026-08-21T05:34:21Z",
      "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": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1156.182973847154,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 20.800006608149722,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 316,
      "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": 120,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-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": 260,
      "max_score": null,
      "measured_at": "2026-08-23T00:03:03Z",
      "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": 316,
      "rating_method": "sequential_elo",
      "raw_elo": 1145.0239194216756,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.691715205934457,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 2,
      "attempted_matches": 196,
      "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": 98,
      "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": 33,
      "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": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1921.5873524622293,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 86.2614975844883,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.695604130687789,
      "unilateral_faults": 0,
      "wins": 163
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:qwen-qwen3-7-max:a50a8f268d5fb73a",
      "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": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:27:25Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1780.9950468049765,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 72.79240290081826,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:claude-fable-5:0d812a1d2c768408",
      "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:28:37Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1769.0766033480754,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 71.7604520313932,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 70
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 190,
      "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": 2,
      "distinct_rated_opponents": 92,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-08-19T21:56:52Z",
      "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": 190,
      "rating_method": "sequential_elo",
      "raw_elo": 1749.555635636583,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 70.02605926216759,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.299737749740931,
      "unilateral_faults": 0,
      "wins": 141
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5-5:d75099c830e67381",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:27:48Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1740.3549601868879,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 69.14142074882011,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 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": "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": 22,
      "max_score": null,
      "measured_at": "2026-08-19T21:22:21Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1713.3713882243446,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 66.56068088153548,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:claude-opus-4-8:7ef4979f6b3e9a70",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:31:22Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1681.4932621274972,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 63.75494931550506,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "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": 56,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "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": 47,
      "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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1656.3784608491428,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 61.55931257885285,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:o3:48e82ad54f426340",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:17:46Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1636.9247706055485,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 59.630586714276724,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5:4164dfc523f2863c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:28:28Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1636.8698724185067,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 59.51888474627783,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 60
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 286,
      "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": 129,
      "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": 120,
      "max_score": null,
      "measured_at": "2026-08-22T19:47:34Z",
      "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": 286,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.677153651903,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 53.4179924942283,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 166
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 196,
      "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": 74,
      "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": 102,
      "max_score": null,
      "measured_at": "2026-08-19T21:21:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1557.3437342280079,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 53.09835437853516,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5-4-mini:84a1457658ce88c0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:19:10Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1562.733366371016,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.68195407315516,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:google-gemini-3-5-flash:602942e58ad38e29",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:34:15Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1543.7114866663292,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.89179952279148,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:z-ai-glm-5-2:f8720fd50b424f28",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T01:11:18Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.4625749629602,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 49.96560708699275,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 48
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 214,
      "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": 2,
      "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": 91,
      "max_score": null,
      "measured_at": "2026-08-22T23:00:29Z",
      "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": 1533.6638531866352,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 49.89528239094483,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 4.817800693045857,
      "unilateral_faults": 0,
      "wins": 123
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 200,
      "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": 2,
      "distinct_rated_opponents": 93,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 95,
      "max_score": null,
      "measured_at": "2026-08-19T21:22:08Z",
      "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": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.7622501223027,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 48.214971045034304,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.00917733558763,
      "unilateral_faults": 0,
      "wins": 105
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:moonshotai-kimi-k2-7-code:d430d8b81bf58172",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:26:41Z",
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.7235320013426,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 47.25397426838036,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 19,
      "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": 9,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-22T15:50:02Z",
      "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": 19,
      "rating_method": "sequential_elo",
      "raw_elo": 1542.484591986778,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.96450843356181,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 68.05339887498948,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:minimax-minimax-m3:f94aa3c94cf69a34",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:34:26Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.907737533893,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.82355270808264,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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:GB2-07:publication-row.v1:balanced:xiaomi-mimo-v2-5-pro:2437b68c7c28667e",
      "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": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:43:24Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.492796093447,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.90229671853825,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:nex-agi-nex-n2-pro:bfccd9446404db2c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:37:00Z",
      "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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.1203052409805,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 42.524739590732,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:qwen-qwen3-7-plus:ea7926e26c1cc685",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T15:18:37Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.7149866418183,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 42.23519271244378,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 57
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:inclusionai-ling-3-0-flash:6f99584b1bad82dc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 52,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 216,
      "max_score": null,
      "measured_at": "2026-08-19T21:22:25Z",
      "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": 380,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.0297347788198,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.40501950685979,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 12.465140987172258,
      "unilateral_faults": 0,
      "wins": 164
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 200,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:xiaomi-mimo-v2-5:f4cab288f8f1ec59",
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T23:37:48Z",
      "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": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.6955545265241,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.113554926110965,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.031155952053808,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:cohere-north-mini-code:b73629af9e588e3b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 38,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 67,
      "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": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.0867753907792,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.36837714419139,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 18.45013723807159,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 204,
      "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": 2,
      "distinct_rated_opponents": 97,
      "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": 125,
      "max_score": null,
      "measured_at": "2026-08-22T06:40:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 204,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.1647760575288,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.295189226700316,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.769741124055803,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:google-gemma-4-31b-it:d0c0442b34151c5a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T21:46:04Z",
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.849027987095,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.232485895385615,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 53
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "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": 24,
      "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": 28,
      "max_score": null,
      "measured_at": "2026-08-23T14:09:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.9786554793234,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.14606416585189,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 194,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5-4-nano:33b97f3221951ed8",
      "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:34:28Z",
      "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": 194,
      "rating_method": "sequential_elo",
      "raw_elo": 1403.2063184617587,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.47050308707877,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.7753885573785855,
      "unilateral_faults": 0,
      "wins": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "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": 10,
      "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": 10,
      "max_score": null,
      "measured_at": "2026-08-22T06:50:33Z",
      "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": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.2408415859013,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.2529709637503,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 70.95786693528086,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 152,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:deepseek-deepseek-v4-flash:ca5e50927e9f8fc5",
      "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": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 89,
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.3669338787731,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.187861256738046,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5-6-terra:02f87be2a684b52a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:18:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1379.3006758761821,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.51437146013137,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 55
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 322,
      "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": 126,
      "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": 191,
      "max_score": null,
      "measured_at": "2026-08-23T10:07:05Z",
      "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": 322,
      "rating_method": "sequential_elo",
      "raw_elo": 1372.8877030640774,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.46251830880079,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 131
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 160,
      "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": 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": "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": 112,
      "max_score": null,
      "measured_at": "2026-08-19T21:43:59Z",
      "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": 160,
      "rating_method": "sequential_elo",
      "raw_elo": 1302.1666353464232,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 28.7988247426727,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:x-ai-grok-build-0-1:40e9bde1c6eafc11",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:38:57Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1249.6710367295523,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 23.186026838702013,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 156,
      "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": 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": "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": 117,
      "max_score": null,
      "measured_at": "2026-08-19T21:22:17Z",
      "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": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1158.879352478688,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 15.276461919221447,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:nvidia-nemotron-3-ultra-550b-a55b:7859dde46c855271",
      "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": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T23:43:45Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1120.4180547333053,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 10.757672736091521,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 156,
      "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": 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": "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": 139,
      "max_score": null,
      "measured_at": "2026-08-22T12:49:16Z",
      "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": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1082.0671538643896,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 8.04764389452622,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:google-gemini-3-1-flash-lite:036cd5692d58f681",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:39:12Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1011.5193889215823,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 0.5504962648416883,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "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": 51,
      "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": 14,
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1930.9765683598841,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 85.92138340901016,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 87
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 206,
      "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": 103,
      "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": 28,
      "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": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1926.3153794356558,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 85.4691894172775,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.280733777820661,
      "unilateral_faults": 0,
      "wins": 178
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 176,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:claude-opus-4-5:6145092901d96725",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "draws": 2,
      "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": 28,
      "max_score": null,
      "measured_at": "2026-08-21T15:41:46Z",
      "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": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1884.3566176372763,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 82.15300774815739,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:claude-fable-5:0d812a1d2c768408",
      "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:34:24Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1817.575241405041,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 74.2473959519865,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 80
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 148,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:google-gemini-3-6-flash:157bc5e3bd81a2f8",
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 35,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:14Z",
      "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": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1758.2226139935103,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 69.12714958998048,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:moonshotai-kimi-k2-7-code:d430d8b81bf58172",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T11:19:09Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1716.3352365750259,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 64.14078623679886,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 58
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 178,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-6-sol:60281ce94ea88014",
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 86,
      "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": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-23T05:21:14Z",
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1714.8191527570873,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 63.78892481747077,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.957067918206963,
      "unilateral_faults": 0,
      "wins": 117
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:meta-muse-spark-1-2:996fe7c6ac30c7b0",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "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": "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": 19,
      "max_score": null,
      "measured_at": "2026-08-21T18:11:34Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1697.4882744755037,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 62.06040464059319,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-5:d75099c830e67381",
      "capped_draws": 50,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-02T22:46:40Z",
      "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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1602.1188603960716,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.85326775023768,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 188,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-4-nano:33b97f3221951ed8",
      "capped_draws": 52,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 92,
      "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-5.4-nano",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T20:41:31Z",
      "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": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1591.1098460751618,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 51.39543114974306,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:qwen-qwen3-8-max:2315ff339b0c18d0",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 7,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 2,
      "max_score": null,
      "measured_at": "2026-08-22T18:02:47Z",
      "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": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1632.9497775865889,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.496905291659246,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 70.95786693528086,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-6-terra:02f87be2a684b52a",
      "capped_draws": 53,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 53,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:28:10Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.0543554717117,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.442997530903185,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 21
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 205,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-4:91029345b4b373cd",
      "capped_draws": 92,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 97,
      "draws": 92,
      "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": 54,
      "max_score": null,
      "measured_at": "2026-08-21T19:14:11Z",
      "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": 205,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.693698947328,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.102704459070644,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.397748846380335,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:o3:48e82ad54f426340",
      "capped_draws": 63,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 63,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:36:48Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.6955904890767,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.04547015939034,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:qwen-qwen3-7-max:a50a8f268d5fb73a",
      "capped_draws": 76,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 76,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:39:17Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.8004114495486,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.640629833593636,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:google-gemini-3-1-flash-lite:036cd5692d58f681",
      "capped_draws": 40,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:18:42Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.8578660442124,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.2403624207267,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-4-mini:84a1457658ce88c0",
      "capped_draws": 41,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 41,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:18:57Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.5819424274005,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.04910404429471,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 35
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:stealth-ox-alpha:03024ebf053d776c",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 21,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 13,
      "max_score": null,
      "measured_at": "2026-08-23T14:11:53Z",
      "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": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.424913229797,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.63090211679806,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:openai-gpt-oss-120b:da344fed618b3552",
      "capped_draws": 86,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 86,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:33:45Z",
      "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": 1421.642551452285,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.70371174356963,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:qwen-qwen3-7-plus:ea7926e26c1cc685",
      "capped_draws": 94,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 94,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:36:50Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.39305533373,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.007945969500966,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:minimax-minimax-m3:f94aa3c94cf69a34",
      "capped_draws": 90,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 90,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:31:56Z",
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.9719926684977,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 33.69443719624106,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:nvidia-nemotron-3-ultra-550b-a55b:7859dde46c855271",
      "capped_draws": 74,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "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": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:39:02Z",
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.0071008564112,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.99164981596408,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:z-ai-glm-5-2:f8720fd50b424f28",
      "capped_draws": 66,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "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": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T03:34:47Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1412.1516499621744,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.90140047086365,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:x-ai-grok-build-0-1:40e9bde1c6eafc11",
      "capped_draws": 93,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 93,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T23:07:13Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.4257773948275,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.89912071233677,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 15,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:thinkingmachines-inkling-small:76482ff3d2fed50c",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 7,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 3,
      "max_score": null,
      "measured_at": "2026-08-21T20:21:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 15,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.0832035786366,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.187114460064755,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 81.25,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:claude-opus-4-8:7ef4979f6b3e9a70",
      "capped_draws": 84,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 84,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T23:29:48Z",
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1395.7974788159802,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.959425881493154,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 200,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:claude-sonnet-5:765bc291b12a711e",
      "capped_draws": 137,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 98,
      "draws": 137,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-08-21T15:02:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1395.6840270777425,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.740890942292665,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.267968709748932,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 164,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:deepseek-deepseek-v4-flash:ca5e50927e9f8fc5",
      "capped_draws": 144,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 82,
      "draws": 144,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 16,
      "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": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1394.044883352306,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.180776324860656,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.144085005109797,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 192,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:moonshotai-kimi-k3:b25ef0843c2d972a",
      "capped_draws": 134,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "draws": 134,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 46,
      "max_score": null,
      "measured_at": "2026-08-21T19:14:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1378.0442055713736,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.092003821784623,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 198,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:xiaomi-mimo-v2-5:f4cab288f8f1ec59",
      "capped_draws": 98,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 94,
      "draws": 98,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T21:46:23Z",
      "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": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1380.240453455008,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.177153598864578,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.296960625842187,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 311,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:meituan-longcat-2-0:26225fa06d2cccd9",
      "capped_draws": 97,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 120,
      "draws": 97,
      "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": 154,
      "max_score": null,
      "measured_at": "2026-08-21T19:14:48Z",
      "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": 311,
      "rating_method": "sequential_elo",
      "raw_elo": 1369.8300630344902,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.932069292243508,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:xiaomi-mimo-v2-5-pro:2437b68c7c28667e",
      "capped_draws": 75,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "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": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T08:41:53Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1367.9946417839965,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.00219316035198,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 204,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-6-luna:56b3e8082c8d4caf",
      "capped_draws": 144,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 98,
      "draws": 144,
      "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": "2026-08-23T09:38:55Z",
      "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": 204,
      "rating_method": "sequential_elo",
      "raw_elo": 1367.5105476995527,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 28.932764092254317,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.769741124055803,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 344,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:poolside-laguna-s-2-1:df6bf1faab8cda70",
      "capped_draws": 235,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 132,
      "draws": 235,
      "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": 95,
      "max_score": null,
      "measured_at": "2026-08-22T11:41:58Z",
      "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": 344,
      "rating_method": "sequential_elo",
      "raw_elo": 1354.0937791457006,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 28.50687633728013,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:cohere-north-mini-code:b73629af9e588e3b",
      "capped_draws": 50,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 34,
      "draws": 80,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 22,
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1368.1606981960256,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 27.151591469186677,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 28.604176007868134,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5:4164dfc523f2863c",
      "capped_draws": 56,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 56,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:19:06Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1347.8497544240654,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.71088363179663,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 8
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 320,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:google-gemini-3-5-flash-lite:ada8852a63812f17",
      "capped_draws": 217,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 120,
      "draws": 217,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 90,
      "max_score": null,
      "measured_at": "2026-08-23T02:42:56Z",
      "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": 320,
      "rating_method": "sequential_elo",
      "raw_elo": 1334.025892170579,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.364688046126368,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 157,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:thinkingmachines-inkling:3ab0a3aec8e194a6",
      "capped_draws": 96,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "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": "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": 50,
      "max_score": null,
      "measured_at": "2026-08-21T18:11:13Z",
      "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": 157,
      "rating_method": "sequential_elo",
      "raw_elo": 1328.7976684792145,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 25.806720683180234,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:google-gemini-3-5-flash:602942e58ad38e29",
      "capped_draws": 68,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "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-3.5-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T02:54:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1332.5013086471351,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 25.159108940712393,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:nex-agi-nex-n2-pro:bfccd9446404db2c",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:33:48Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1194.9426957801345,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 11.297346143143717,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 8
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:claude-opus-5:e9ebdf808117b870",
      "capped_draws": 0,
      "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": 70.35475020724844,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 327,
      "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": "2026-08-21T15:53:02Z",
      "losses": 257,
      "max_score": 91.17466067700593,
      "measured_at": null,
      "min_score": 51.08859351407519,
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1525,
      "rating_method": "sequential_elo",
      "raw_elo": 1753.8817152612887,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 68.04487783235751,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 941
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:moonshotai-kimi-k3:5a54aec150052f73",
      "capped_draws": 0,
      "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": 52.163081702045574,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 416,
      "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": "2026-08-23T04:48:24Z",
      "losses": 377,
      "max_score": 96.03018425662745,
      "measured_at": null,
      "min_score": 22.900288191407675,
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1396,
      "rating_method": "sequential_elo",
      "raw_elo": 1574.9829607075385,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 52.163081702045574,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 603
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-6-sol:34bccf96d771d2e5",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 17
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.14688374999999998,
        "mean": 0.12438640625,
        "median": 0.12834374999999998,
        "min": 0.09558187500000001,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 17
        },
        "run_count": 17,
        "token_priced_attempt_count": 17,
        "total": 2.0924099999999997
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 49.80429606555579,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 355,
      "eligibility_flag": true,
      "entry_count": 16,
      "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": [
        "GB2-04"
      ],
      "first_pass_admitted": 8,
      "first_pass_rate": 0.8888888888888888,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 8,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T03:03:24Z",
      "losses": 414,
      "max_score": 64.58767896133882,
      "measured_at": null,
      "min_score": 26.469312004278905,
      "model_code_failure_rate": 0.1111111111111111,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": 0.8888888888888888,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1412,
      "rating_method": "sequential_elo",
      "raw_elo": 1566.1022879989719,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 48.359151871005515,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 643
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-4:86f20e721b83e093",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 20
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.16978625,
        "mean": 0.09482640625,
        "median": 0.07918125000000001,
        "min": 0.06869,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 20
        },
        "run_count": 16,
        "token_priced_attempt_count": 20,
        "total": 1.5172225000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 47.31507124816302,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 487,
      "eligibility_flag": true,
      "entry_count": 16,
      "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": "2026-08-22T07:54:09Z",
      "losses": 394,
      "max_score": 86.15134182727353,
      "measured_at": null,
      "min_score": 18.245710919802534,
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1448,
      "rating_method": "sequential_elo",
      "raw_elo": 1553.5301452408119,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 47.31507124816302,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 567
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:claude-opus-4-5:5c9da2cc66629f89",
      "capped_draws": 0,
      "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": 46.955420779375146,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 278,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 222,
      "max_score": 69.43814796420975,
      "measured_at": null,
      "min_score": 25.52082770903801,
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 782,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.5528321320671,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 46.955420779375146,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 282
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:claude-opus-4-8:78901219e94b3137",
      "capped_draws": 0,
      "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": 46.4863977297371,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 160,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 193,
      "max_score": 69.78217372191577,
      "measured_at": null,
      "min_score": 18.694108648166214,
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 622,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.645900733587,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 44.96016608783939,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 269
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:x-ai-grok-4-5:0d820700fd8c1f0b",
      "capped_draws": 0,
      "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": 0.5947036000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 44.881496329176954,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 403,
      "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": "2026-08-23T13:45:16Z",
      "losses": 390,
      "max_score": 83.79628828599199,
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1275,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.6217428347632,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 44.881496329176954,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 482
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:z-ai-glm-5-2:79cd8062a2dce9fb",
      "capped_draws": 0,
      "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": 42.11163766096654,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 386,
      "eligibility_flag": true,
      "entry_count": 16,
      "evaluated_setting_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": 408,
      "max_score": 57.774334362784295,
      "measured_at": null,
      "min_score": 16.009458011887702,
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1172,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.5080965058962,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 42.11163766096654,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 378
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:claude-sonnet-5:5d48f6168d64e7fe",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 17,
        "cell_count": 8,
        "cost_basis_counts": {
          "estimated": 1,
          "local_list_price_estimate": 16,
          "provider_dashboard_reconciled": 1
        },
        "evidence_basis": "Combined: Provider-reported + Recorded attempt + Standard list-price estimate",
        "max": 0.078265,
        "mean": 0.06253833333333332,
        "median": 0.0614995,
        "min": 0.050688,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 17
        },
        "recorded_attempt_count": 2,
        "run_count": 17,
        "token_priced_attempt_count": 16,
        "total": 1.07324
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.01139025216278,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 641,
      "eligibility_flag": true,
      "entry_count": 17,
      "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": "2026-08-23T12:40:55Z",
      "losses": 523,
      "max_score": 54.18705207861794,
      "measured_at": null,
      "min_score": 21.114044974233778,
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1635,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.8360288436243,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 42.01139025216278,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 471
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-6-terra:667397b0870c7a77",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.1192425,
        "mean": 0.0683559375,
        "median": 0.06152125,
        "min": 0.0542775,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 10
        },
        "run_count": 9,
        "token_priced_attempt_count": 10,
        "total": 0.6063375
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 41.9029728616441,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 309,
      "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-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": 7,
      "first_pass_rate": 0.7777777777777778,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_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",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 8,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:05:30Z",
      "losses": 252,
      "max_score": 53.15064951506388,
      "measured_at": null,
      "min_score": 28.399082893812732,
      "model_code_failure_rate": 0.1111111111111111,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": 0.8888888888888888,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 774,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.7672841080807,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 1,
      "repaired_rate": 0.1111111111111111,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 40.68709706880698,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 213
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:qwen-qwen3-7-max:aa6ab832c76ea81e",
      "capped_draws": 0,
      "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": 40.86417247608275,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 223,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": 224,
      "max_score": 65.56652347725021,
      "measured_at": null,
      "min_score": 23.986859461426256,
      "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": 652,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.1761545693928,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 39.52252855229327,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 205
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:deepseek-deepseek-v4-pro:e8d00a0b6ffa9a25",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.029078938,
        "mean": 0.015562441375000001,
        "median": 0.013116718500000001,
        "min": 0.005612805,
        "recorded_attempt_count": 12,
        "run_count": 8,
        "total": 0.124499531
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.828102714361634,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 234,
      "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-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:27:08Z",
      "losses": 217,
      "max_score": 64.1672924244156,
      "measured_at": null,
      "min_score": 21.894015414373516,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": 0.875,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 672,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.3580308625667,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 39.4876430254095,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 221
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:google-gemini-3-5-flash-lite:d8ea2a1333ff0452",
      "capped_draws": 0,
      "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": 0.27157109999999995
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 40.115968605994766,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 773,
      "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": "2026-08-23T12:51:52Z",
      "losses": 858,
      "max_score": 69.37028762269674,
      "measured_at": null,
      "min_score": 9.276903456466506,
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2311,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.3447395325536,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 39.473905934702984,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 680
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-4-1:4599845cc619bbdb",
      "capped_draws": 0,
      "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": 39.175380343627474,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 260,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 271,
      "max_score": 54.37710879884957,
      "measured_at": null,
      "min_score": 17.324048509285905,
      "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": 749,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.519885077438,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 39.175380343627474,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 218
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:meta-muse-spark-1-2:772fc6bb6f83c6c9",
      "capped_draws": 0,
      "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": 39.043450885870016,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 166,
      "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": "2026-08-23T09:38:06Z",
      "losses": 299,
      "max_score": 57.58895419336781,
      "measured_at": null,
      "min_score": 16.50878695816217,
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 692,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.068833992935,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 39.043450885870016,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 227
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-5:f6e479886e809751",
      "capped_draws": 0,
      "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": 39.74621893216972,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 354,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": 187,
      "max_score": 51.810059046408426,
      "measured_at": null,
      "min_score": 22.09524395964808,
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 696,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.6233072985822,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 38.44127942421412,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 155
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:tencent-hy3-preview:569c7bc7bedf8ce3",
      "capped_draws": 0,
      "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": 39.18764503209153,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 248,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": 150,
      "max_score": 71.07282896064237,
      "measured_at": null,
      "min_score": 14.388654431203785,
      "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": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 550,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.701921748651,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 36.46821288363263,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 152
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:poolside-laguna-s-2-1:834cbfa8b37e299a",
      "capped_draws": 0,
      "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": 37.835105981413676,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 461,
      "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": "2026-08-22T23:51:52Z",
      "losses": 460,
      "max_score": 54.815141934474596,
      "measured_at": null,
      "min_score": 18.971051988167996,
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1333,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.8829661717682,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 36.40476713567153,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 412
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:google-gemini-3-6-flash:497c5e32f5a0da50",
      "capped_draws": 0,
      "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": 36.37905054510748,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 909,
      "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": "2026-08-23T13:45:16Z",
      "losses": 937,
      "max_score": 52.7743268035604,
      "measured_at": null,
      "min_score": 17.072829141107093,
      "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": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2531,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.0944924382118,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 36.37905054510748,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 685
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:minimax-minimax-m3:214bcd6c65e8f3eb",
      "capped_draws": 0,
      "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": 38.2144104593529,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 134,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": 227,
      "max_score": 49.061655826617994,
      "measured_at": null,
      "min_score": 16.721194515766282,
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 586,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.5517427700706,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 35.5625160611959,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 12,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-4-nano:6279438894c15a9b",
      "capped_draws": 0,
      "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": 37.47825265467621,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 340,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": 433,
      "max_score": 53.78745945851931,
      "measured_at": null,
      "min_score": 19.073029071771302,
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1130,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.6486709701255,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 34.877444031097845,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 357
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:a987a47e59219899",
      "capped_draws": 0,
      "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": 36.17912444280867,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 178,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": 209,
      "max_score": 55.212486240190024,
      "measured_at": null,
      "min_score": 12.615617756799654,
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 524,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.7480939277336,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 33.97597552234614,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 137
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:xiaomi-mimo-v2-5:bc21a02f757e23f7",
      "capped_draws": 0,
      "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": 0.00169122,
        "recorded_attempt_count": 37,
        "run_count": 24,
        "total": 0.0689052158
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 36.67030236955936,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 420,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": 589,
      "max_score": 46.37515439857774,
      "measured_at": null,
      "min_score": 19.548028827872443,
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1498,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.7022329007111,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 33.391249190889106,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 489
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:thinkingmachines-inkling:70a9ac993f011430",
      "capped_draws": 0,
      "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": 0.5884539500000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 35.47310379880186,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 387,
      "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": "2026-08-05T05:41:54Z",
      "losses": 496,
      "max_score": 67.94308497290339,
      "measured_at": null,
      "min_score": 12.59254361838801,
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1222,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.9508598295226,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 33.01144276259816,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 339
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:meituan-longcat-2-0:8409ccd1edce8105",
      "capped_draws": 0,
      "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": 33.67094708059916,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 526,
      "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": "2026-08-05T05:41:26Z",
      "losses": 541,
      "max_score": 56.21511165223179,
      "measured_at": null,
      "min_score": 14.601235431191899,
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1442,
      "rating_method": "sequential_elo",
      "raw_elo": 1394.6982609142556,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 32.565469621454156,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 375
    },
    {
      "admitted_plugins": 28,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:stealth-ox-alpha:2a6c37bfc1ea9a10",
      "capped_draws": 0,
      "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": 30.666233135237924,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 83,
      "eligibility_flag": true,
      "entry_count": 22,
      "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": "2026-08-23T15:12:59Z",
      "losses": 155,
      "max_score": 43.15000174191575,
      "measured_at": null,
      "min_score": 3.872072017351666,
      "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": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 321,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.0019137585691,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 30.141830768739514,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-4-mini:1967d37331d30497",
      "capped_draws": 0,
      "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": 29.208084954343278,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 344,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": 267,
      "max_score": 42.50170870197985,
      "measured_at": null,
      "min_score": 7.8623797518037435,
      "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": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 738,
      "rating_method": "sequential_elo",
      "raw_elo": 1354.3385270828308,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 29.208084954343278,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 127
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:deepseek-deepseek-v4-flash:423951efbfeea85e",
      "capped_draws": 0,
      "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": 0.00408087,
        "mean": 0.0022664345375,
        "median": 0.0017928150000000001,
        "min": 0.0013289177,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.0181314763
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 28.29631741105212,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 253,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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"
      ],
      "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": "2026-08-05T05:23:15Z",
      "losses": 257,
      "max_score": 39.99912971379366,
      "measured_at": null,
      "min_score": 16.918306920549412,
      "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": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 646,
      "rating_method": "sequential_elo",
      "raw_elo": 1360.900688836864,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 27.36729866382614,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 136
    },
    {
      "admitted_plugins": 10,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:inclusionai-ling-3-0-flash:4838b994eb665922",
      "capped_draws": 0,
      "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": 27.734523333650188,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 676,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 440,
      "max_score": 40.10360954415184,
      "measured_at": null,
      "min_score": 15.779988068257042,
      "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": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1320,
      "rating_method": "sequential_elo",
      "raw_elo": 1357.2292455919485,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 24.659865895737095,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 204
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:qwen-qwen3-7-plus:a8d8ab3b2b52478f",
      "capped_draws": 0,
      "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": 26.44462943801278,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 180,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": 255,
      "max_score": 45.76839619365652,
      "measured_at": null,
      "min_score": 4.247286587507169,
      "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": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 551,
      "rating_method": "sequential_elo",
      "raw_elo": 1331.383402614363,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 23.89542014490823,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-6-luna:1c8c41335b2357b1",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 17
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.006186499999999999,
        "mean": 0.0044960124999999995,
        "median": 0.004244175,
        "min": 0.0036738749999999996,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 17
        },
        "run_count": 16,
        "token_priced_attempt_count": 17,
        "total": 0.0719362
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 20.751124293312085,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 499,
      "eligibility_flag": true,
      "entry_count": 16,
      "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": 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": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 8,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T12:40:55Z",
      "losses": 751,
      "max_score": 37.83935796116576,
      "measured_at": null,
      "min_score": 10.864694550855324,
      "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": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1414,
      "rating_method": "sequential_elo",
      "raw_elo": 1268.8045453843365,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 20.751124293312085,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 164
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:google-gemini-3-1-flash-lite:483a08d2c98ab52c",
      "capped_draws": 0,
      "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": 0.04706875
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 17.4455680741114,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 85,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": 212,
      "max_score": 39.0195992003968,
      "measured_at": null,
      "min_score": 0.0,
      "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": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 370,
      "rating_method": "sequential_elo",
      "raw_elo": 1230.0089436034125,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 15.511547251312342,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:openai-gpt-oss-120b:bd210de776e73710",
      "capped_draws": 0,
      "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": 0.0032939400000000004,
        "mean": 0.0016413085000000001,
        "median": 0.0014119655,
        "min": 0.00045831,
        "recorded_attempt_count": 13,
        "run_count": 8,
        "total": 0.013130468000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 14.781157625670273,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 244,
      "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": "openai/gpt-oss-120b",
        "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"
      ],
      "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": "2026-08-23T13:45:04Z",
      "losses": 738,
      "max_score": 22.92523467244584,
      "measured_at": null,
      "min_score": 0.0,
      "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": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1146,
      "rating_method": "sequential_elo",
      "raw_elo": 1192.6216498361186,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 14.2958657645256,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 164
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-4-1-nano:e6370d2aaad0f23a",
      "capped_draws": 0,
      "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-2026-08-08": 1
        },
        "recorded_attempt_count": 1,
        "run_count": 1,
        "token_priced_attempt_count": 1,
        "total": 0.0023425
      },
      "codegen_evaluated_cells": 1,
      "conditional_success_score": 40.511310783890416,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 39,
      "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-14T22:12:59Z",
      "losses": 69,
      "max_score": 40.511310783890416,
      "measured_at": null,
      "min_score": 40.511310783890416,
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.1019623450045,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 40.511310783890416,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:df1c628cc31cb288",
      "capped_draws": 0,
      "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": 39.50775450335153,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 140,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:17:07Z",
      "losses": 201,
      "max_score": 50.20183268472181,
      "measured_at": null,
      "min_score": 25.222210730949445,
      "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": 558,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.0192237543772,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 38.01418194663798,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:qwen-qwen3-8-max:3a653d034173d2f2",
      "capped_draws": 0,
      "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": 0.9576840000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 34.240469798169755,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 54,
      "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": "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T02:23:52Z",
      "losses": 45,
      "max_score": 61.919231042616644,
      "measured_at": null,
      "min_score": 7.491362721335916,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.1639275216203,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 34.240469798169755,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:thinkingmachines-inkling-small:2a1c609d5f09a424",
      "capped_draws": 0,
      "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": 32.34497402709219,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 50,
      "eligibility_flag": false,
      "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T08:13:39Z",
      "losses": 61,
      "max_score": 41.144919554096006,
      "measured_at": null,
      "min_score": 15.025055106927441,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 141,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.5612353522909,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 31.4064374924807,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:google-gemma-4-31b-it:e747a6997aa21289",
      "capped_draws": 0,
      "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": 31.150644590364873,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 190,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [
        "GB2-02"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:48:11Z",
      "losses": 255,
      "max_score": 42.432414819587265,
      "measured_at": null,
      "min_score": 17.377509992236185,
      "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": 608,
      "rating_method": "sequential_elo",
      "raw_elo": 1335.852594591143,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 29.973008744719447,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 163
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:stepfun-step-3-7-flash:283efeb922617cca",
      "capped_draws": 0,
      "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": 0.19924717999999997
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 35.208732986034015,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 115,
      "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": "2026-08-23T10:07:05Z",
      "losses": 330,
      "max_score": 50.91082045936282,
      "measured_at": null,
      "min_score": 22.117549019522556,
      "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": 650,
      "rating_method": "sequential_elo",
      "raw_elo": 1368.955564881608,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 29.606897353581214,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 205
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:nex-agi-nex-n2-pro:2f1571320c21662f",
      "capped_draws": 0,
      "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": 2.586028
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 36.33161686261811,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 295,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": 197,
      "max_score": 60.50605278337446,
      "measured_at": null,
      "min_score": 16.55738720588751,
      "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": 652,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.242976410029,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 29.54807821865933,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 160
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:mistralai-mistral-medium-3-5:34da7964c6511272",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.06200699999999999,
        "mean": 0.042994687499999996,
        "median": 0.0423105,
        "min": 0.0223935,
        "recorded_attempt_count": 14,
        "run_count": 8,
        "total": 0.34395749999999997
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 34.34821004798081,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 109,
      "eligibility_flag": false,
      "entry_count": 4,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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",
        "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:02:41Z",
      "losses": 170,
      "max_score": 39.8933469399602,
      "measured_at": null,
      "min_score": 27.922700568650274,
      "model_code_failure_rate": 0.5,
      "model_code_failures": 4,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": 0.5,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 405,
      "rating_method": "sequential_elo",
      "raw_elo": 1365.418014434873,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 28.88328669972868,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 126
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:o3:647217df3b12bb67",
      "capped_draws": 0,
      "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-2026-08-08": 8
        },
        "recorded_attempt_count": 8,
        "run_count": 8,
        "token_priced_attempt_count": 13,
        "total": 0.8831579999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 26.89816985159589,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 185,
      "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": "2026-08-23T12:51:52Z",
      "losses": 353,
      "max_score": 51.58180645988167,
      "measured_at": null,
      "min_score": 7.743053185185025,
      "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": 663,
      "rating_method": "sequential_elo",
      "raw_elo": 1287.4934568187057,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 22.61857460509252,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 125
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:baseline:cohere-north-mini-code:3e6a1897cfdaa330",
      "capped_draws": 0,
      "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": 26.84117147848124,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 194,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 255,
      "max_score": 32.78188345286514,
      "measured_at": null,
      "min_score": 23.07648794314826,
      "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": 536,
      "rating_method": "sequential_elo",
      "raw_elo": 1311.1508350569354,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 20.068456528448355,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 198,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-4:86f20e721b83e093",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 90,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 26,
      "max_score": null,
      "measured_at": "2026-08-19T23:52:11Z",
      "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": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1890.5204580260204,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 86.15134182727353,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 160
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:tencent-hy3-preview:569c7bc7bedf8ce3",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:08:37Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1740.5175222083988,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 71.07282896064237,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:claude-opus-5:e9ebdf808117b870",
      "capped_draws": 105,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 117,
      "draws": 105,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-08-05T05:16:51Z",
      "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": 241,
      "rating_method": "sequential_elo",
      "raw_elo": 1717.6654625146953,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 69.11820487491038,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.6112092379023624,
      "unilateral_faults": 0,
      "wins": 113
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 186,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-6-sol:34bccf96d771d2e5",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 87,
      "draws": 12,
      "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": 50,
      "max_score": null,
      "measured_at": "2026-08-19T22:28:34Z",
      "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": 180,
      "rating_method": "sequential_elo",
      "raw_elo": 1678.48173230548,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 64.58767896133882,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 118
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-4-1:4599845cc619bbdb",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 49,
      "max_score": null,
      "measured_at": "2026-08-05T04:26:53Z",
      "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": 113,
      "rating_method": "sequential_elo",
      "raw_elo": 1572.9878368669815,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.37710879884957,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.079290579084697,
      "unilateral_faults": 1,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:qwen-qwen3-7-max:aa6ab832c76ea81e",
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "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": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T02:19:50Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1573.513576219901,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.19394021291321,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 202,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-4-nano:6279438894c15a9b",
      "capped_draws": 54,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 96,
      "draws": 54,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:01:18Z",
      "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": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1569.9906928986984,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 53.78745945851931,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.625533144189548,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:a987a47e59219899",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T03:24:08Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.6985011257657,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.991414623983445,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:claude-opus-4-8:78901219e94b3137",
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 23,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 24,
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.0122470382578,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.971032291512834,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-6-terra:667397b0870c7a77",
      "capped_draws": 30,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 30,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:05:30Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.0809635791695,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 51.380928870298845,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:minimax-minimax-m3:214bcd6c65e8f3eb",
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "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": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:20:28Z",
      "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": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.7090711594628,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 49.061655826617994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-5:f6e479886e809751",
      "capped_draws": 92,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 92,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:09:23Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.7226018234821,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 47.92198712859516,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 11
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 314,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:xiaomi-mimo-v2-5:bc21a02f757e23f7",
      "capped_draws": 63,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 156,
      "draws": 63,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 134,
      "max_score": null,
      "measured_at": "2026-08-05T01:58:44Z",
      "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": 314,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.4191526249888,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.37515439857774,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.085107523100876,
      "unilateral_faults": 0,
      "wins": 117
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 203,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:moonshotai-kimi-k3:5a54aec150052f73",
      "capped_draws": 139,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "draws": 139,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 32,
      "max_score": null,
      "measured_at": "2026-08-20T02:03:00Z",
      "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": 203,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.9678850754415,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.72944773324043,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 3,
      "attempted_matches": 381,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:claude-sonnet-5:5d48f6168d64e7fe",
      "capped_draws": 170,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 163,
      "draws": 170,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-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": 116,
      "max_score": null,
      "measured_at": "2026-08-23T12:40:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 381,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.937341958395,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.681065340229,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.943289360496225,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 209,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:x-ai-grok-4-5:0d820700fd8c1f0b",
      "capped_draws": 134,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "draws": 134,
      "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": 36,
      "max_score": null,
      "measured_at": "2026-08-23T09:56:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 209,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.140841118312,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.4844504231055,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 2,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:poolside-laguna-s-2-1:834cbfa8b37e299a",
      "capped_draws": 54,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 116,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 108,
      "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": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.0026155738424,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.7867759390862,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.7092032923910905,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:deepseek-deepseek-v4-pro:e8d00a0b6ffa9a25",
      "capped_draws": 46,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:27:08Z",
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.1514954467345,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 42.49233284225822,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:google-gemma-4-31b-it:e747a6997aa21289",
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:13:53Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.704251657997,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 42.432414819587265,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 19,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:thinkingmachines-inkling-small:2a1c609d5f09a424",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "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": "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": 7,
      "max_score": null,
      "measured_at": "2026-08-22T09:27:15Z",
      "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": 19,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.0445342877708,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.144919554096006,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 68.05339887498948,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 168,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-4-1-nano:e6370d2aaad0f23a",
      "capped_draws": 39,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 39,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-08-14T22:12:59Z",
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.1019623450045,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.511310783890416,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 136,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:mistralai-mistral-medium-3-5:34da7964c6511272",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:02:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 101,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.8243444955588,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.8933469399602,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.757377148833722,
      "unilateral_faults": 35,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:claude-opus-4-5:5c9da2cc66629f89",
      "capped_draws": 77,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 77,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 26,
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.0475483689286,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.60642935936982,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:df1c628cc31cb288",
      "capped_draws": 32,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "draws": 32,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:19:05Z",
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.395743836614,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.18442894600758,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 354,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:google-gemini-3-5-flash-lite:d8ea2a1333ff0452",
      "capped_draws": 83,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 134,
      "draws": 83,
      "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": 160,
      "max_score": null,
      "measured_at": "2026-08-22T14:46:36Z",
      "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": 354,
      "rating_method": "sequential_elo",
      "raw_elo": 1388.3550597099304,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.47267278277283,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 111
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 314,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:inclusionai-ling-3-0-flash:4838b994eb665922",
      "capped_draws": 101,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 117,
      "draws": 101,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 120,
      "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": 314,
      "rating_method": "sequential_elo",
      "raw_elo": 1385.0409369204554,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.951635842394275,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 93
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:stealth-ox-alpha:2a6c37bfc1ea9a10",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 21,
      "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": "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": 27,
      "max_score": null,
      "measured_at": "2026-08-23T12:17:06Z",
      "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": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.826841528916,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.16566098009839,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:meta-muse-spark-1-2:772fc6bb6f83c6c9",
      "capped_draws": 39,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "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": "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": 44,
      "max_score": null,
      "measured_at": "2026-08-23T09:38:06Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1367.3882021779489,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 33.19164564959547,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:meituan-longcat-2-0:8409ccd1edce8105",
      "capped_draws": 82,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 115,
      "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": "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": 95,
      "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": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1358.3905602002214,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.811959377744365,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.5464209114540584,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-4-mini:1967d37331d30497",
      "capped_draws": 40,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 40,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:15:42Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1351.113886438586,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.866704468526944,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 156,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:z-ai-glm-5-2:79cd8062a2dce9fb",
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 78,
      "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": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T03:20:17Z",
      "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": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1325.5609213423263,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 28.603518652489697,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:qwen-qwen3-8-max:3a653d034173d2f2",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 1,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-08-22T07:23:00Z",
      "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": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1364.0547383269693,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 27.24176104741712,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:qwen-qwen3-7-plus:a8d8ab3b2b52478f",
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "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": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T23:49:57Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1300.7914998768108,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.630246682212057,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 348,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:google-gemini-3-6-flash:497c5e32f5a0da50",
      "capped_draws": 82,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 131,
      "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-3.6-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": 186,
      "max_score": null,
      "measured_at": "2026-08-22T16:31:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 348,
      "rating_method": "sequential_elo",
      "raw_elo": 1257.316022774441,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 23.202887647175736,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 2,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:cohere-north-mini-code:3e6a1897cfdaa330",
      "capped_draws": 98,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 106,
      "draws": 98,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 105,
      "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": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1263.538009086365,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 23.07648794314826,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.387218039620898,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 193,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-6-luna:1c8c41335b2357b1",
      "capped_draws": 44,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 92,
      "draws": 44,
      "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": 123,
      "max_score": null,
      "measured_at": "2026-08-23T12:40:55Z",
      "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": 190,
      "rating_method": "sequential_elo",
      "raw_elo": 1231.1251946973412,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.48303910660878,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.314301757134349,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 176,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:openai-gpt-oss-120b:bd210de776e73710",
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 70,
      "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": "openai/gpt-oss-120b",
        "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": 113,
      "max_score": null,
      "measured_at": "2026-08-22T09:27:15Z",
      "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": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1217.332032382236,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.17906841539228,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:thinkingmachines-inkling:70a9ac993f011430",
      "capped_draws": 84,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 109,
      "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": "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": 124,
      "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": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1159.2375706062403,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 12.59254361838801,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.6751283820590555,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:google-gemini-3-1-flash-lite:483a08d2c98ab52c",
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T03:26:44Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1144.1569784358514,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 10.214928346057336,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 166,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:o3:647217df3b12bb67",
      "capped_draws": 48,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 48,
      "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": 111,
      "max_score": null,
      "measured_at": "2026-08-20T02:24:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1105.068326196998,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 7.743053185185025,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 186,
      "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": 93,
      "draws": 76,
      "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": 14,
      "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": 186,
      "rating_method": "sequential_elo",
      "raw_elo": 1654.4005500316935,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 62.66869493063295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 96
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-5-6-terra:667397b0870c7a77",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 91,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:51:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.4681276807262,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 28.399082893812732,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 127,
      "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": 50,
      "draws": 113,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-08-23T03:23:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 127,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.590095915884,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 27.457151552126646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.444173824159213,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 144,
      "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": 2,
      "distinct_rated_opponents": 67,
      "draws": 118,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-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": 14,
      "max_score": null,
      "measured_at": "2026-08-23T03:03:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.6624599764757,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.469312004278905,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 14.787054914327616,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:claude-opus-4-5:5c9da2cc66629f89",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 78,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "2026-08-04T21:44:58Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.645381413465,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 25.52082770903801,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:df1c628cc31cb288",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "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": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T08:48:42Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.2790874838233,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 25.222210730949445,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 102,
      "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": 50,
      "draws": 90,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 10,
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.3681592549508,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 24.925858625367727,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:qwen-qwen3-7-max:aa6ab832c76ea81e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "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": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T23:04:52Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.2151308299296,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 23.986859461426256,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 154,
      "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": 57,
      "draws": 136,
      "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": 10,
      "max_score": null,
      "measured_at": "2026-08-19T23:37:33Z",
      "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": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.0575574041725,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 22.900288191407675,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-5-5:f6e479886e809751",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "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-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T23:05:09Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.225904404823,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 22.09524395964808,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:deepseek-deepseek-v4-pro:e8d00a0b6ffa9a25",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 80,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T15:08:17Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.8446177830178,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 21.894015414373516,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 164,
      "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": 2,
      "distinct_rated_opponents": 79,
      "draws": 142,
      "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": 18,
      "max_score": null,
      "measured_at": "2026-08-23T03:04:42Z",
      "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": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.2242536105712,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 21.114044974233778,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.569000256975185,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:google-gemini-3-1-flash-lite:483a08d2c98ab52c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T03:32:23Z",
      "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": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.5240632772964,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 20.925483752639348,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-5-4-mini:1967d37331d30497",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 84,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T22:55:23Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.998408715422,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.57568162564367,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:xiaomi-mimo-v2-5:bc21a02f757e23f7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 65,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.8584606204145,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.548028827872443,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 256,
      "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": 97,
      "draws": 234,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-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": 20,
      "max_score": null,
      "measured_at": "2026-08-22T08:45:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.157553055973,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.535834131740515,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.3089127354028465,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:deepseek-deepseek-v4-flash:423951efbfeea85e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 80,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:29:01Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.6834789339953,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.168036379032152,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 174,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-5-4-nano:6279438894c15a9b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 87,
      "draws": 156,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:33:25Z",
      "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": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.5162308159042,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.073029071771302,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.552760371103872,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "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": 52,
      "draws": 99,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 4,
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.0890590046167,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 18.971051988167996,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "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": 50,
      "draws": 94,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.7390320719044,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 18.862874029135362,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-4-1:4599845cc619bbdb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 72,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 12,
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.2386314581393,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 18.7319500025143,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:claude-opus-4-8:78901219e94b3137",
      "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 5,
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.7697346783725,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 18.694108648166214,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 158,
      "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": 2,
      "distinct_rated_opponents": 73,
      "draws": 142,
      "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": 14,
      "max_score": null,
      "measured_at": "2026-08-22T07:54:09Z",
      "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": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.0378659484488,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 18.245710919802534,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 12.313100169977513,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:qwen-qwen3-7-plus:a8d8ab3b2b52478f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "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": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:59:50Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.658322014426,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 17.570880513249598,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 150,
      "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": 2,
      "distinct_rated_opponents": 74,
      "draws": 142,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-20T02:43:51Z",
      "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": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.570548826457,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 17.153724083661814,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 14.061497018246985,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 252,
      "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": 94,
      "draws": 229,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-08-23T03:03:24Z",
      "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": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.4683467098837,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 17.072829141107093,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.6667408666858066,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:inclusionai-ling-3-0-flash:4838b994eb665922",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 110,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.7308308182332,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 16.871313010451086,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:minimax-minimax-m3:214bcd6c65e8f3eb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "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": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:33:21Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.210402384003,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 16.721194515766282,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:nex-agi-nex-n2-pro:2f1571320c21662f",
      "capped_draws": 0,
      "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": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:32:40Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.0500885064464,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 16.55738720588751,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "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": 31,
      "draws": 57,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-19T21:57:00Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.6017691862596,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 16.50878695816217,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 128,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:z-ai-glm-5-2:79cd8062a2dce9fb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 64,
      "draws": 118,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T03:32:32Z",
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.8538739796686,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 16.009458011887702,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "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": 9,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 0,
      "max_score": null,
      "measured_at": "2026-08-22T09:26:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.6020204364095,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 15.025055106927441,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 70.95786693528086,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:tencent-hy3-preview:569c7bc7bedf8ce3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "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": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T02:27:36Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.8163020312015,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 14.388654431203785,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 17,
      "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": 8,
      "draws": 14,
      "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": 3,
      "max_score": null,
      "measured_at": "2026-08-22T08:45:10Z",
      "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": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.545523222252,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 7.491362721335916,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 74.10113019775793,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 42,
      "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": 21,
      "draws": 28,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-08-23T14:09:45Z",
      "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": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.4161473966744,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 3.872072017351666,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 158,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:moonshotai-kimi-k3:5a54aec150052f73",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "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": "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": 40,
      "max_score": null,
      "measured_at": "2026-08-22T17:46:55Z",
      "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": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1571.4990999527986,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 57.255056886144494,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 2,
      "attempted_matches": 176,
      "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": 88,
      "draws": 35,
      "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": 56,
      "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": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1561.558435222868,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.44510087203772,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.259934288992827,
      "unilateral_faults": 0,
      "wins": 85
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 172,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:claude-sonnet-5:5d48f6168d64e7fe",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 84,
      "draws": 67,
      "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": 44,
      "max_score": null,
      "measured_at": "2026-08-20T23:23:22Z",
      "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": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1560.1492778884449,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.18705207861794,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.866254227491025,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 43,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "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": 36,
      "max_score": null,
      "measured_at": "2026-08-22T17:46:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1549.3266540892673,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.90544213032362,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 176,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:google-gemini-3-5-flash-lite:d8ea2a1333ff0452",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 68,
      "draws": 52,
      "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": 51,
      "max_score": null,
      "measured_at": "2026-08-22T20:29:46Z",
      "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": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1532.6867109455625,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.19326999050381,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 324,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:google-gemini-3-6-flash:497c5e32f5a0da50",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 129,
      "draws": 107,
      "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": 90,
      "max_score": null,
      "measured_at": "2026-08-22T17:46:55Z",
      "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": 324,
      "rating_method": "sequential_elo",
      "raw_elo": 1521.8275933200516,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.541598092506504,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 127
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-4-1:4599845cc619bbdb",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 28,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 31,
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1521.331600253054,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 48.831744011327004,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:claude-opus-4-5:5c9da2cc66629f89",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 15,
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1517.64293491248,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 48.527410514780094,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-6-terra:667397b0870c7a77",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 36,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T13:39:17Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1515.2761169916803,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 47.862625672133966,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 168,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:thinkingmachines-inkling:70a9ac993f011430",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 82,
      "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": "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": 37,
      "max_score": null,
      "measured_at": "2026-08-05T05:23:15Z",
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1513.9841261509482,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 47.82588085262712,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 10.527724777936779,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-4-nano:6279438894c15a9b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 34,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:02:45Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.4667049734755,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.59618183026941,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 28
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 174,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03: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": 2,
      "distinct_rated_opponents": 84,
      "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-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": 44,
      "max_score": null,
      "measured_at": "2026-08-23T02:31:42Z",
      "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": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.6335378998199,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.4254670635394,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.614857365683216,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:xiaomi-mimo-v2-5:bc21a02f757e23f7",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 41,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:02:34Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.2810908524089,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.280998303857686,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 21
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 178,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-4:86f20e721b83e093",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 83,
      "draws": 84,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 51,
      "max_score": null,
      "measured_at": "2026-08-21T11:43:42Z",
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.1634271005496,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.46667985844482,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.074719125763062,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:z-ai-glm-5-2:79cd8062a2dce9fb",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 58,
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T02:51:28Z",
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.8935207156142,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.17948587926281,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 21.37252890985009,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-4-mini:1967d37331d30497",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "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-5.4-mini",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.8658260094098,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 42.50170870197985,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:minimax-minimax-m3:214bcd6c65e8f3eb",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "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": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:55:23Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.257046359489,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.31640418901639,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03: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": 9,
      "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": "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": 4,
      "max_score": null,
      "measured_at": "2026-08-22T11:01:47Z",
      "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": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.121643907326,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.08868410464794,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 251,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:poolside-laguna-s-2-1:834cbfa8b37e299a",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 112,
      "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": "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": 77,
      "max_score": null,
      "measured_at": "2026-08-22T23:51:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 251,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.4006292034796,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.927445639857304,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:tencent-hy3-preview:569c7bc7bedf8ce3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 30,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:49:50Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.882558264278,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.551433143204484,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:df1c628cc31cb288",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 41,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:17:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.8646223820033,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.40303950625073,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:nex-agi-nex-n2-pro:2f1571320c21662f",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "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": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T15:07:00Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.1051582810692,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.07029226565205,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-5:f6e479886e809751",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 36,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:23:57Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.1973645808223,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.29934502959449,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:deepseek-deepseek-v4-flash:423951efbfeea85e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:23:15Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.6399776232663,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.61116549844097,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:qwen-qwen3-7-max:aa6ab832c76ea81e",
      "capped_draws": 6,
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T04:31:38Z",
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.0472522295584,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.201572417188274,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 172,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-6-luna:1c8c41335b2357b1",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 80,
      "draws": 89,
      "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": 59,
      "max_score": null,
      "measured_at": "2026-08-23T05:19:28Z",
      "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": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.4951997173266,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 33.3734962639214,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 10.026656325279454,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:deepseek-deepseek-v4-pro:e8d00a0b6ffa9a25",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T22:38:18Z",
      "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": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.1567925431275,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.83797916630326,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 15,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:qwen-qwen3-8-max:3a653d034173d2f2",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "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": "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": 7,
      "max_score": null,
      "measured_at": "2026-08-22T20:29:46Z",
      "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": 15,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.2371045770194,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.071719571532732,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 81.25,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:a987a47e59219899",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "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": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T02:59:43Z",
      "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": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1393.790497688098,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.736891928612994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 166,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:meituan-longcat-2-0:8409ccd1edce8105",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 79,
      "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": "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": 54,
      "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": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1380.8913638836275,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.66163798427531,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 10.830591148722647,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 28,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:stealth-ox-alpha:2a6c37bfc1ea9a10",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 12,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 10,
      "max_score": null,
      "measured_at": "2026-08-23T15:12:59Z",
      "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": 23,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.2308212149396,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.634239899442424,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 97.46252452815364,
      "unilateral_faults": 1,
      "wins": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 200,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:inclusionai-ling-3-0-flash:4838b994eb665922",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 79,
      "draws": 87,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 77,
      "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": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1361.644886820065,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 27.56514642169852,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.00917733558763,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 152,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:openai-gpt-oss-120b:bd210de776e73710",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 63,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 78,
      "max_score": null,
      "measured_at": "2026-08-22T23:51:52Z",
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1273.1146500874393,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 16.522204329731178,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 162,
      "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": 64,
      "draws": 42,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 111,
      "max_score": null,
      "measured_at": "2026-08-22T17:42:01Z",
      "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": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1150.82535220259,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 102,
      "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": 51,
      "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": "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": 24,
      "max_score": null,
      "measured_at": "2026-08-05T05:32:31Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1584.2614626043232,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 56.21511165223179,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 22
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 204,
      "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": 102,
      "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": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:33:21Z",
      "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": 204,
      "rating_method": "sequential_elo",
      "raw_elo": 1550.6547495671625,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 51.08859351407519,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:claude-opus-4-5:5c9da2cc66629f89",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 50,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 14,
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.6081087252508,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.534733628873596,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 156,
      "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": 63,
      "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": "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": 31,
      "max_score": null,
      "measured_at": "2026-08-23T04:48:24Z",
      "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": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.343293683398,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.69357274580004,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:gpt-5-6-terra:667397b0870c7a77",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "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-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:20:19Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1521.160171149716,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.206877878735085,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 8
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 264,
      "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": 101,
      "draws": 163,
      "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": 45,
      "max_score": null,
      "measured_at": "2026-08-23T01:51:58Z",
      "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": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.2420234775436,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.281108867143885,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.13627265814059708,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:tencent-hy3-preview:569c7bc7bedf8ce3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:48:07Z",
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1506.6569734340017,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.249796081077825,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 15
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 154,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:z-ai-glm-5-2:79cd8062a2dce9fb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 77,
      "draws": 100,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T02:43:08Z",
      "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": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.1231788792588,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.08531679812856,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 12.951351796455231,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 160,
      "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": 2,
      "distinct_rated_opponents": 79,
      "draws": 113,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-21T20:36:03Z",
      "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": 160,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.810449180274,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 42.553343702010935,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.920326830426156,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 164,
      "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": 2,
      "distinct_rated_opponents": 78,
      "draws": 117,
      "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": 21,
      "max_score": null,
      "measured_at": "2026-08-22T13:00:23Z",
      "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": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.3374206322035,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 42.11981237248688,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:a987a47e59219899",
      "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T02:30:53Z",
      "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": 1498.4721260722356,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.455613711503254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:gpt-5-5:f6e479886e809751",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 66,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:02:26Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.1646241939861,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.222856430705775,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:inclusionai-ling-3-0-flash:4838b994eb665922",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 102,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 7,
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.192389292363,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.10360954415184,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 280,
      "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": 106,
      "draws": 218,
      "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": 40,
      "max_score": null,
      "measured_at": "2026-08-23T13:45:16Z",
      "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": 280,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.01042909638,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.81555278408415,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 76,
      "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": 36,
      "draws": 54,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-08-22T06:51:04Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.7694515360909,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.7944295068769,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:claude-opus-4-8:78901219e94b3137",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 60,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 15,
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.1348689981835,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.727863503836645,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:google-gemma-4-31b-it:e747a6997aa21289",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "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": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:48:11Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.369156952384,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.60896936866197,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 144,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:xiaomi-mimo-v2-5:bc21a02f757e23f7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 72,
      "draws": 113,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T02:31:22Z",
      "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": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.5782235231818,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.57531415912807,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 14.787054914327616,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 15,
      "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": 8,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 0,
      "max_score": null,
      "measured_at": "2026-08-21T20:01:27Z",
      "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": 15,
      "rating_method": "sequential_elo",
      "raw_elo": 1525.0357629986581,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.941404265071526,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 81.25,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 166,
      "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": 2,
      "distinct_rated_opponents": 81,
      "draws": 120,
      "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": 28,
      "max_score": null,
      "measured_at": "2026-08-22T06:51:04Z",
      "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": 1468.0684066313174,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.83935796116576,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 10.877144523309603,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:nex-agi-nex-n2-pro:2f1571320c21662f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 83,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:13:44Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.340110846728,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.74168060162787,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:qwen-qwen3-7-plus:a8d8ab3b2b52478f",
      "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": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.91418843072,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.7416657545222,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:gpt-5-4-mini:1967d37331d30497",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "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-5.4-mini",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:24:08Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.0297776195794,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.883321001904825,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:gpt-4-1:4599845cc619bbdb",
      "capped_draws": 0,
      "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 14,
      "max_score": null,
      "measured_at": "2026-08-05T05:32:45Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.7387499700872,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.31202602070684,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 178,
      "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": 87,
      "draws": 124,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 32,
      "max_score": null,
      "measured_at": "2026-08-05T05:32:49Z",
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.3475549764407,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.67352159482515,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.9766057392055,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 173,
      "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": 2,
      "distinct_rated_opponents": 81,
      "draws": 113,
      "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": 37,
      "max_score": null,
      "measured_at": "2026-08-22T04:12:04Z",
      "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": 173,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.7929324162299,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.34395455370223,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.73435719754701,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 133,
      "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": 51,
      "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": "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": 21,
      "max_score": null,
      "measured_at": "2026-08-23T13:45:16Z",
      "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": 133,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.310826299396,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 33.17065439419427,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 22,
      "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": 11,
      "draws": 17,
      "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": 4,
      "max_score": null,
      "measured_at": "2026-08-23T01:51:58Z",
      "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": 22,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.4779270736012,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.32099723181149,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 60.5072070285374,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "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": 24,
      "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": "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": 16,
      "max_score": null,
      "measured_at": "2026-08-23T12:24:56Z",
      "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": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.7350302187187,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.9119831179808,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:deepseek-deepseek-v4-flash:423951efbfeea85e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:54:22Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1363.997401760583,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 21.587325373198095,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:openai-gpt-oss-120b:bd210de776e73710",
      "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": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 71,
      "max_score": null,
      "measured_at": "2026-08-23T02:43:04Z",
      "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": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1210.9553390354572,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 238,
      "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": 119,
      "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": 24,
      "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": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1976.4988138269168,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 87.54201134418061,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.8947351529780132,
      "unilateral_faults": 0,
      "wins": 214
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 182,
      "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": 2,
      "distinct_rated_opponents": 89,
      "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": 57,
      "max_score": null,
      "measured_at": "2026-08-15T02:19:58Z",
      "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": 182,
      "rating_method": "sequential_elo",
      "raw_elo": 1682.3424943016976,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 62.68439698336576,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.380913286308589,
      "unilateral_faults": 0,
      "wins": 125
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 17,
      "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": 9,
      "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": 0,
      "max_score": null,
      "measured_at": "2026-08-22T14:19:11Z",
      "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": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1725.7042357575813,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 61.919231042616644,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 74.10113019775793,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 185,
      "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": 77,
      "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": 65,
      "max_score": null,
      "measured_at": "2026-08-20T13:06:17Z",
      "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": 185,
      "rating_method": "sequential_elo",
      "raw_elo": 1633.2331677471427,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 59.63400603920557,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 120
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:a987a47e59219899",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T02:29:42Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1593.0579629263639,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 55.212486240190024,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 55
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 188,
      "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": 2,
      "distinct_rated_opponents": 92,
      "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": 75,
      "max_score": null,
      "measured_at": "2026-08-22T11:11:03Z",
      "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": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1587.2834483300476,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.84370148624712,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.5830662995282605,
      "unilateral_faults": 0,
      "wins": 113
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 196,
      "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": 98,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 71,
      "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": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1586.099222433189,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.815141934474596,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.532690756236184,
      "unilateral_faults": 0,
      "wins": 125
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:claude-opus-4-5:5c9da2cc66629f89",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 40,
      "max_score": null,
      "measured_at": "2026-08-05T02:32:47Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1584.2090805580165,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.787452361508244,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-5-6-terra:667397b0870c7a77",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:20:58Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1567.3066590038927,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 53.15064951506388,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "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": 43,
      "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": 42,
      "max_score": null,
      "measured_at": "2026-08-20T12:15:34Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.788333723547,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 53.02456786594432,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-5-5:f6e479886e809751",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:40:34Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1551.1627362890197,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 51.810059046408426,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:qwen-qwen3-7-max:aa6ab832c76ea81e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:40:38Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1515.586736592979,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 49.08905663197634,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 53
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 341,
      "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": 133,
      "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": 148,
      "max_score": null,
      "measured_at": "2026-08-22T23:45:14Z",
      "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": 341,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.2181493329292,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 48.89848482079757,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 193
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 166,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:z-ai-glm-5-2:79cd8062a2dce9fb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "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": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T03:35:07Z",
      "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": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.119904446422,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 48.88616759311684,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 84
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 161,
      "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": 65,
      "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": 85,
      "max_score": null,
      "measured_at": "2026-08-22T23:41:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 161,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.9702034985373,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.31767802468079,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:qwen-qwen3-7-plus:a8d8ab3b2b52478f",
      "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": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:37:44Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.341736666781,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.76839619365652,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:minimax-minimax-m3:214bcd6c65e8f3eb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T11:38:28Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.3464738181478,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.19689169842294,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:nex-agi-nex-n2-pro:2f1571320c21662f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T11:29:18Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.6103813613147,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.77294290610812,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 53
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "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": 24,
      "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": 23,
      "max_score": null,
      "measured_at": "2026-08-23T14:12:11Z",
      "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": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.807691416014,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.09989722408759,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:df1c628cc31cb288",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:50:04Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.8486850159818,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.08775105458573,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 52
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 256,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:xiaomi-mimo-v2-5:bc21a02f757e23f7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 128,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 133,
      "max_score": null,
      "measured_at": "2026-08-03T14:20:34Z",
      "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": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.1145701397409,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 42.291871269429016,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 10.06462264614784,
      "unilateral_faults": 0,
      "wins": 123
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:deepseek-deepseek-v4-flash:423951efbfeea85e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:55:59Z",
      "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": 1404.752960189545,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.99912971379366,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:deepseek-deepseek-v4-pro:e8d00a0b6ffa9a25",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T11:37:30Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1393.141045545112,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.79395147095302,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:claude-opus-4-8:78901219e94b3137",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 55,
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1386.8051899721886,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.26782236702627,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 43
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 192,
      "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": 2,
      "distinct_rated_opponents": 95,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-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": 109,
      "max_score": null,
      "measured_at": "2026-08-22T14:19:11Z",
      "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": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1384.3832545267173,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.030311469462845,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.04972212351036,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:mistralai-mistral-medium-3-5:34da7964c6511272",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T11:38:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1351.468176625996,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.33343869093166,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:tencent-hy3-preview:569c7bc7bedf8ce3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:56:04Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1329.3883779909766,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 33.59671726886273,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 154,
      "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": 56,
      "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": 99,
      "max_score": null,
      "measured_at": "2026-08-22T10:50:26Z",
      "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": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1299.4636047831602,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.650235307750318,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 2,
      "attempted_matches": 214,
      "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": 107,
      "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": 142,
      "max_score": null,
      "measured_at": "2026-08-05T03:40:47Z",
      "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": 1298.8487134830848,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.105118393569768,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.376451717525809,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-5-4-mini:1967d37331d30497",
      "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:40:16Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1258.1950094624974,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 27.518483895121314,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "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": 7,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-08-20T12:05:25Z",
      "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": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1275.2637241074317,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 24.72348845861986,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 70.95786693528086,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 178,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-5-4-nano:6279438894c15a9b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 89,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 136,
      "max_score": null,
      "measured_at": "2026-08-05T04:56:12Z",
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1169.1766725591847,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 20.032859834975213,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.957067918206963,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:google-gemma-4-31b-it:e747a6997aa21289",
      "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": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:32:27Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1136.0733751755404,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 17.377509992236185,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-4-1:4599845cc619bbdb",
      "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 66,
      "max_score": null,
      "measured_at": "2026-08-05T04:55:59Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1135.4295707705774,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 17.324048509285905,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 28
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 180,
      "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": 2,
      "distinct_rated_opponents": 86,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 138,
      "max_score": null,
      "measured_at": "2026-08-22T10:50:31Z",
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1135.7254816048269,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 17.25377681257326,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.9766057392055,
      "unilateral_faults": 2,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:google-gemini-3-1-flash-lite:483a08d2c98ab52c",
      "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": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T03:34:49Z",
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1136.308456520139,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 17.067829071463514,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 19
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 182,
      "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": 89,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 130,
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1103.7825250791311,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 14.601235431191899,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.9766057392055,
      "unilateral_faults": 4,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 189,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:openai-gpt-oss-120b:bd210de776e73710",
      "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": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "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": 153,
      "max_score": null,
      "measured_at": "2026-08-23T13:45:04Z",
      "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": 189,
      "rating_method": "sequential_elo",
      "raw_elo": 1087.1904502695809,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 14.31642168470547,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 326,
      "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": 118,
      "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": 277,
      "max_score": null,
      "measured_at": "2026-08-22T19:33:48Z",
      "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": 324,
      "rating_method": "sequential_elo",
      "raw_elo": 1028.8157077908918,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 9.276903456466506,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 104,
      "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": 52,
      "draws": 11,
      "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": 5,
      "max_score": null,
      "measured_at": "2026-08-03T14:04:35Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1978.901816863329,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 91.17466067700593,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 88
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 180,
      "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": 2,
      "distinct_rated_opponents": 85,
      "draws": 13,
      "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": 40,
      "max_score": null,
      "measured_at": "2026-08-20T18:11:07Z",
      "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": 180,
      "rating_method": "sequential_elo",
      "raw_elo": 1748.6796558739966,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 71.00824638840129,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.749961355672497,
      "unilateral_faults": 0,
      "wins": 127
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:deepseek-deepseek-v4-pro:e8d00a0b6ffa9a25",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T11:04:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1670.4616001827212,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 64.1672924244156,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 184,
      "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": 68,
      "draws": 20,
      "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": 70,
      "max_score": null,
      "measured_at": "2026-08-20T21:14:21Z",
      "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": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1623.3658987890403,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 61.25978450989219,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 94
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 302,
      "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": 113,
      "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-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": 116,
      "max_score": null,
      "measured_at": "2026-08-23T03:04:24Z",
      "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": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1620.4034216639773,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 60.74100437018801,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 182
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:z-ai-glm-5-2:79cd8062a2dce9fb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 75,
      "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": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T20:22:51Z",
      "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": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1599.5647166016763,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 57.774334362784295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.637484322183244,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:claude-opus-4-8:78901219e94b3137",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 30,
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.4794101376715,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.6517518521781,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:gpt-4-1:4599845cc619bbdb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 35,
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1555.174459690298,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.318655446755876,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 180,
      "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": 2,
      "distinct_rated_opponents": 86,
      "draws": 7,
      "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": 84,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:37Z",
      "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": 180,
      "rating_method": "sequential_elo",
      "raw_elo": 1534.6153480768362,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.49882564269781,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.702272173073723,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 163,
      "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": 60,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "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": 68,
      "max_score": null,
      "measured_at": "2026-08-22T18:02:35Z",
      "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": 163,
      "rating_method": "sequential_elo",
      "raw_elo": 1506.1558845685156,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.965291500953946,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 164,
      "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": 60,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 68,
      "max_score": null,
      "measured_at": "2026-08-20T21:54:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.431236228724,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.91082045936282,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 193,
      "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": 2,
      "distinct_rated_opponents": 92,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 86,
      "max_score": null,
      "measured_at": "2026-08-22T11:41:43Z",
      "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": 193,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.428107503386,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.53096191919179,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.911460911719565,
      "unilateral_faults": 0,
      "wins": 101
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 196,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:gpt-5-4-nano:6279438894c15a9b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 96,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:41:10Z",
      "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": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.2372841051183,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 49.76392479065197,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.5095838835902065,
      "unilateral_faults": 0,
      "wins": 109
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 216,
      "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": 106,
      "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": "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": 108,
      "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": 216,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.432472937302,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.215404534608886,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.293407807185584,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 268,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:xiaomi-mimo-v2-5:bc21a02f757e23f7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 132,
      "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": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 136,
      "max_score": null,
      "measured_at": "2026-08-05T03:20:33Z",
      "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": 268,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.4837446514557,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.33777259514364,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.996538749078123,
      "unilateral_faults": 0,
      "wins": 128
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:claude-opus-4-5:5c9da2cc66629f89",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 44,
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.511289483019,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.871714707416494,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 3,
      "attempted_matches": 42,
      "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": 21,
      "draws": 1,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-08-23T14:12:18Z",
      "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": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.8317645204697,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.15000174191575,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:df1c628cc31cb288",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T09:47:39Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.6211054795062,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 42.94726409759388,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:google-gemini-3-1-flash-lite:483a08d2c98ab52c",
      "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": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T02:02:44Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1381.2364236832755,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.0195992003968,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:gpt-5-6-terra:667397b0870c7a77",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:04:35Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1373.9806181391325,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.82721709336295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:gpt-5-4-mini:1967d37331d30497",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:29:03Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1335.615860264783,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.44117680027425,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 21,
      "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": 10,
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-23T00:33:30Z",
      "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": 21,
      "rating_method": "sequential_elo",
      "raw_elo": 1368.9037533119765,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.421477251042134,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 62.850358177805205,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:mistralai-mistral-medium-3-5:34da7964c6511272",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:42:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1323.4952044044514,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.24335399238109,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "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": 54,
      "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": 58,
      "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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1315.7125886364151,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 33.94239152620984,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:google-gemma-4-31b-it:e747a6997aa21289",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:42:50Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1313.9232512674864,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 33.633332893697606,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 41
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 329,
      "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": 118,
      "draws": 35,
      "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": 212,
      "max_score": null,
      "measured_at": "2026-08-23T09:38:44Z",
      "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": 329,
      "rating_method": "sequential_elo",
      "raw_elo": 1254.9959580997784,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.256284231675217,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "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": 10,
      "draws": 2,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-08-22T23:34:51Z",
      "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": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1320.8161587044958,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.24798627908666,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "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": 43,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-08-20T21:45:35Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1250.7317045501534,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 28.027781786573513,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:a987a47e59219899",
      "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": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T02:45:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1244.3425660567527,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 27.180737771836384,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 99,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:qwen-qwen3-7-plus:a8d8ab3b2b52478f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:19:33Z",
      "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": 99,
      "rating_method": "sequential_elo",
      "raw_elo": 1234.4468531079099,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.709300896929104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.25,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:qwen-qwen3-7-max:aa6ab832c76ea81e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:41:50Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1225.4277449994963,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 25.9118827156635,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "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": 52,
      "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": 58,
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1210.0954507274137,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 24.749232472982165,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:nex-agi-nex-n2-pro:2f1571320c21662f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:20:18Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1204.3990254582595,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 23.982876833913124,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 171,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:openai-gpt-oss-120b:bd210de776e73710",
      "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": "openai/gpt-oss-120b",
        "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": 121,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:37Z",
      "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": 171,
      "rating_method": "sequential_elo",
      "raw_elo": 1181.1910568908093,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 22.92523467244584,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 1,
      "attempted_matches": 168,
      "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": 62,
      "draws": 26,
      "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": 115,
      "max_score": null,
      "measured_at": "2026-08-20T21:45:46Z",
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1154.7845709020912,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 20.618239276105058,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:deepseek-deepseek-v4-flash:423951efbfeea85e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "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-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:19:58Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1123.1640710825773,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 16.918306920549412,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:inclusionai-ling-3-0-flash:4838b994eb665922",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 100,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 192,
      "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": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1103.1532899366941,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 15.779988068257042,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.13627265814059708,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 182,
      "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": 2,
      "distinct_rated_opponents": 88,
      "draws": 3,
      "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": 155,
      "max_score": null,
      "measured_at": "2026-08-22T23:34:51Z",
      "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": 1085.7034588483796,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 13.698238650426038,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.380913286308589,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "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": 50,
      "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": 22,
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1856.1879837603456,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 80.15897505759567,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 146,
      "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": 57,
      "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": 33,
      "max_score": null,
      "measured_at": "2026-08-22T14:34:56Z",
      "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": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1761.1992839087297,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 71.8604564523625,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 113
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 298,
      "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": 117,
      "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": 97,
      "max_score": null,
      "measured_at": "2026-08-22T15:50:15Z",
      "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": 298,
      "rating_method": "sequential_elo",
      "raw_elo": 1734.4124904712762,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 69.37028762269674,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:qwen-qwen3-7-max:aa6ab832c76ea81e",
      "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": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T08:56:19Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1703.2609653449783,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 65.56652347725021,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:nex-agi-nex-n2-pro:2f1571320c21662f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:14:11Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1648.1717121399788,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 60.50605278337446,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 67
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 185,
      "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": 2,
      "distinct_rated_opponents": 89,
      "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": 77,
      "max_score": null,
      "measured_at": "2026-08-22T19:47:34Z",
      "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": 185,
      "rating_method": "sequential_elo",
      "raw_elo": 1594.516713772066,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 55.385642848862844,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.959323524730464,
      "unilateral_faults": 0,
      "wins": 108
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 315,
      "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": 116,
      "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": 147,
      "max_score": null,
      "measured_at": "2026-08-23T02:42:49Z",
      "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": 311,
      "rating_method": "sequential_elo",
      "raw_elo": 1557.3822819538093,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.7743268035604,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 164
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 166,
      "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": 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": "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": 80,
      "max_score": null,
      "measured_at": "2026-08-23T08:55:50Z",
      "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": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1543.6832616568183,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 51.58180645988167,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:claude-opus-4-8:78901219e94b3137",
      "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 39,
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1550.4563465439146,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 51.31003172352387,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 57
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 211,
      "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": 100,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 113,
      "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": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 1544.010143590685,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.79810134192654,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.759161709357059,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:df1c628cc31cb288",
      "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": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:50:32Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.1060983283344,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.20183268472181,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-4-1:4599845cc619bbdb",
      "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-4.1",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 48,
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1530.801634444942,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 49.29223370785008,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 152,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:z-ai-glm-5-2:79cd8062a2dce9fb",
      "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": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T03:28:43Z",
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.489111184017,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 47.92684620493954,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 19,
      "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": 10,
      "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": 7,
      "max_score": null,
      "measured_at": "2026-08-23T02:23:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 19,
      "rating_method": "sequential_elo",
      "raw_elo": 1558.924963586655,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 47.51171651636437,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 68.05339887498948,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 184,
      "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": 2,
      "distinct_rated_opponents": 90,
      "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": 96,
      "max_score": null,
      "measured_at": "2026-08-19T21:31:53Z",
      "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": 1504.3555571524566,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.88742950850896,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.133601128499478,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-5-5:f6e479886e809751",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:02:22Z",
      "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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.820592135627,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.53174665691214,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:claude-opus-4-5:5c9da2cc66629f89",
      "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 53,
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.297529638152,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.356649989805135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:deepseek-deepseek-v4-pro:e8d00a0b6ffa9a25",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:28:45Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.5598229415996,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.51464116371525,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 208,
      "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": 102,
      "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": 103,
      "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": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.1612694805494,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.853186603425755,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.071586885778516,
      "unilateral_faults": 0,
      "wins": 105
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "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": 24,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-08-23T12:27:10Z",
      "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": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.0816236736982,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.908636824800936,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-5-6-terra:667397b0870c7a77",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:43:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.8298422557973,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.10393902588812,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 178,
      "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": 68,
      "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": 109,
      "max_score": null,
      "measured_at": "2026-08-23T10:07:05Z",
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1378.7192000023038,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.156327157500364,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:minimax-minimax-m3:214bcd6c65e8f3eb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:09:17Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1367.2693290956158,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 33.90216158577543,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 20,
      "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": 11,
      "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": 14,
      "max_score": null,
      "measured_at": "2026-08-23T08:13:39Z",
      "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": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.8173258582663,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 33.305573503838346,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "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": 42,
      "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": 58,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:30Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1339.6829441858488,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.305998996116344,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:deepseek-deepseek-v4-flash:423951efbfeea85e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T00:20:40Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1337.0075281912582,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.9614054899469,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "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": 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": "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": 56,
      "max_score": null,
      "measured_at": "2026-08-05T04:09:52Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1320.0660988276552,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.776430806523866,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 48
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 176,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:xiaomi-mimo-v2-5:bc21a02f757e23f7",
      "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": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T22:56:47Z",
      "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": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1316.8492403373612,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.134310310413017,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.552760371103872,
      "unilateral_faults": 2,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-5-4-nano:6279438894c15a9b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T11:10:49Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1303.316043587365,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 28.128038323977535,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 184,
      "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": 2,
      "distinct_rated_opponents": 86,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 114,
      "max_score": null,
      "measured_at": "2026-08-19T21:22:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1302.6352816290546,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 27.903476569312414,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.133601128499478,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 178,
      "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": 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": "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": 121,
      "max_score": null,
      "measured_at": "2026-08-19T21:34:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1289.9508601455611,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 27.802313254046688,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 194,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:cohere-north-mini-code:3e6a1897cfdaa330",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 89,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 130,
      "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": 190,
      "rating_method": "sequential_elo",
      "raw_elo": 1267.58485647528,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 24.665143039430337,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.33305067329769,
      "unilateral_faults": 4,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:google-gemma-4-31b-it:e747a6997aa21289",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T21:49:16Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1217.1234130773007,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.726281854437815,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 2,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:a987a47e59219899",
      "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": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T03:28:04Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1144.8702182648058,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 12.615617756799654,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 12
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 179,
      "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": 2,
      "distinct_rated_opponents": 85,
      "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": 148,
      "max_score": null,
      "measured_at": "2026-08-23T02:42:49Z",
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1122.2584672517671,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 10.864694550855324,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.9766057392055,
      "unilateral_faults": 1,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 168,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:openai-gpt-oss-120b:bd210de776e73710",
      "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": "openai/gpt-oss-120b",
        "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": 142,
      "max_score": null,
      "measured_at": "2026-08-22T14:34:56Z",
      "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": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1108.1862556209687,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 10.614346337124728,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-5-4-mini:1967d37331d30497",
      "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-5.4-mini",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T01:46:38Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1090.5750082161858,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 7.8623797518037435,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 2,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:qwen-qwen3-7-plus:a8d8ab3b2b52478f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T01:12:37Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1053.14781558953,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 4.247286587507169,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 2,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:google-gemini-3-1-flash-lite:483a08d2c98ab52c",
      "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/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T03:28:34Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1010.8187961005,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 178,
      "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": 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": "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": 8,
      "max_score": null,
      "measured_at": "2026-08-21T19:14:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 2021.4459228627536,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 96.03018425662745,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 170
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 174,
      "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": 72,
      "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": 27,
      "max_score": null,
      "measured_at": "2026-08-22T18:02:47Z",
      "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": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1900.781455166142,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 83.79628828599199,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 147
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:claude-opus-4-8:78901219e94b3137",
      "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 25,
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1773.8635077665217,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 69.78217372191577,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:claude-opus-4-5:5c9da2cc66629f89",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 6,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 19,
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1770.4607839572238,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 69.43814796420975,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:thinkingmachines-inkling:70a9ac993f011430",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 37,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1751.0420667004444,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 67.94308497290339,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 70
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 276,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:claude-opus-5:e9ebdf808117b870",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 119,
      "draws": 16,
      "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": 57,
      "max_score": null,
      "measured_at": "2026-08-21T15:53:02Z",
      "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": 276,
      "rating_method": "sequential_elo",
      "raw_elo": 1735.1859103033014,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 66.64176038754904,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.4376202060078436,
      "unilateral_faults": 0,
      "wins": 203
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 184,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-6-sol:34bccf96d771d2e5",
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 88,
      "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-5.6-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": 47,
      "max_score": null,
      "measured_at": "2026-08-22T23:22:38Z",
      "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": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1667.474883572294,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 59.07179186850058,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 112
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:meta-muse-spark-1-2:772fc6bb6f83c6c9",
      "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": "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": 33,
      "max_score": null,
      "measured_at": "2026-08-21T18:12:16Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1653.2616124943645,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 57.58895419336781,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 53
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:z-ai-glm-5-2:79cd8062a2dce9fb",
      "capped_draws": 64,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 75,
      "draws": 64,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T20:23:06Z",
      "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": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1586.4595448981868,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.42797378512286,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.697319232624107,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 196,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-4-nano:6279438894c15a9b",
      "capped_draws": 95,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 97,
      "draws": 95,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:41:31Z",
      "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": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1526.837067851132,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.966275272568765,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.695604130687789,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:deepseek-deepseek-v4-pro:e8d00a0b6ffa9a25",
      "capped_draws": 82,
      "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": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T03:56:58Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.1908415956534,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.09650651851254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:minimax-minimax-m3:214bcd6c65e8f3eb",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-02T23:32:13Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.5181338037046,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.08815494051834,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:qwen-qwen3-8-max:3a653d034173d2f2",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 7,
      "draws": 13,
      "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": 0,
      "max_score": null,
      "measured_at": "2026-08-21T20:35:50Z",
      "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": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1535.5507689243868,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.11898397519311,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 202,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:claude-sonnet-5:5d48f6168d64e7fe",
      "capped_draws": 142,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 98,
      "draws": 142,
      "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": 32,
      "max_score": null,
      "measured_at": "2026-08-15T01:49:26Z",
      "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": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.212748355298,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.139049301541,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.165321546996081,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-5:f6e479886e809751",
      "capped_draws": 83,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "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-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:22:27Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.0693276623153,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.342294273323965,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:tencent-hy3-preview:569c7bc7bedf8ce3",
      "capped_draws": 90,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 90,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:32:28Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.9497965630508,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.26644030755798,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-4-1:4599845cc619bbdb",
      "capped_draws": 79,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "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-4.1",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 16,
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.4565971654238,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.21527625173018,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:google-gemma-4-31b-it:e747a6997aa21289",
      "capped_draws": 94,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "draws": 94,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T22:07:22Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.9221194161503,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.12535861356842,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:a987a47e59219899",
      "capped_draws": 78,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 78,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-07-31T02:32:37Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.0047853601131,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.06110906673491,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:deepseek-deepseek-v4-flash:423951efbfeea85e",
      "capped_draws": 88,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 88,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:55:50Z",
      "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": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.0594040768221,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.82885250240368,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:cohere-north-mini-code:3e6a1897cfdaa330",
      "capped_draws": 96,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 96,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.3296396091612,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.78188345286514,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 201,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-4:86f20e721b83e093",
      "capped_draws": 129,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 94,
      "draws": 129,
      "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": 55,
      "max_score": null,
      "measured_at": "2026-08-21T19:14:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 201,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.0690466304977,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.716762885001636,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.93393038013303,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:nex-agi-nex-n2-pro:2f1571320c21662f",
      "capped_draws": 96,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "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": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:41:06Z",
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1403.0243582764076,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.69008544176368,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:qwen-qwen3-7-max:aa6ab832c76ea81e",
      "capped_draws": 76,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 76,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:33:39Z",
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1397.181675768906,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.09937241616148,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-4-mini:1967d37331d30497",
      "capped_draws": 77,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "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-5.4-mini",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T06:58:48Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1400.3144399361822,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.01522338949161,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 2,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-6-terra:667397b0870c7a77",
      "capped_draws": 74,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 74,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T07:10:17Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.0357740645313,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.292461943857255,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 2,
      "wins": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:meituan-longcat-2-0:8409ccd1edce8105",
      "capped_draws": 200,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 109,
      "draws": 200,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 22,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:26Z",
      "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": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1386.927401056984,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.146167032179893,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.6751283820590555,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 14,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:thinkingmachines-inkling-small:2a1c609d5f09a424",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 6,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 4,
      "max_score": null,
      "measured_at": "2026-08-21T20:35:50Z",
      "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": 14,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.7011179104888,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.109189972494256,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 85.34944487358055,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:poolside-laguna-s-2-1:834cbfa8b37e299a",
      "capped_draws": 195,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 109,
      "draws": 195,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1383.4836426691504,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.797992553400974,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.6751283820590555,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 318,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:inclusionai-ling-3-0-flash:4838b994eb665922",
      "capped_draws": 272,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 118,
      "draws": 272,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 37,
      "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": 314,
      "rating_method": "sequential_elo",
      "raw_elo": 1371.6131397638803,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.13544711494835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 346,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:google-gemini-3-6-flash:497c5e32f5a0da50",
      "capped_draws": 238,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 129,
      "draws": 238,
      "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": 92,
      "max_score": null,
      "measured_at": "2026-08-23T00:15:43Z",
      "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": 346,
      "rating_method": "sequential_elo",
      "raw_elo": 1363.5371582184212,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.47044083995327,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 2,
      "attempted_matches": 343,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:google-gemini-3-5-flash-lite:d8ea2a1333ff0452",
      "capped_draws": 237,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 127,
      "draws": 237,
      "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": 92,
      "max_score": null,
      "measured_at": "2026-08-23T12:51:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 343,
      "rating_method": "sequential_elo",
      "raw_elo": 1349.6849491452738,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 28.056667626445826,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:mistralai-mistral-medium-3-5:34da7964c6511272",
      "capped_draws": 92,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "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": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:49:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1354.8843322134849,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 27.922700568650274,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 163,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:o3:647217df3b12bb67",
      "capped_draws": 111,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "draws": 111,
      "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": 47,
      "max_score": null,
      "measured_at": "2026-08-23T12:51:52Z",
      "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": 163,
      "rating_method": "sequential_elo",
      "raw_elo": 1346.4376685189152,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 27.649580485211807,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 188,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:xiaomi-mimo-v2-5:bc21a02f757e23f7",
      "capped_draws": 134,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 94,
      "draws": 134,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:41:45Z",
      "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": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1348.0333804561371,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.81896909205326,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.557446496601106,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 28,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:stealth-ox-alpha:2a6c37bfc1ea9a10",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 14,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 17,
      "max_score": null,
      "measured_at": "2026-08-23T14:12:04Z",
      "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": 28,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.0853900991224,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 25.587373276225822,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 85.34944487358055,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 158,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:stepfun-step-3-7-flash:283efeb922617cca",
      "capped_draws": 104,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 104,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 54,
      "max_score": null,
      "measured_at": "2026-08-23T09:38:55Z",
      "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": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1292.208218512245,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 22.117549019522556,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 158,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:openai-gpt-oss-120b:bd210de776e73710",
      "capped_draws": 94,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "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": "openai/gpt-oss-120b",
        "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": 60,
      "max_score": null,
      "measured_at": "2026-08-23T02:22:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1270.3817645663387,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.910827940292407,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 2,
      "attempted_matches": 198,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-6-luna:1c8c41335b2357b1",
      "capped_draws": 101,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 96,
      "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-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": 92,
      "max_score": null,
      "measured_at": "2026-08-22T11:52:09Z",
      "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": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1243.4896054972753,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 16.34266691728431,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.402778048576745,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:claude-fable-5:5a1cc0fafbb266c7",
      "capped_draws": 0,
      "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": 1.91725,
        "mean": 1.58262125,
        "median": 1.5854,
        "min": 1.05322,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 12.66097
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 83.8181052528922,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 98,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "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": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04"
      ],
      "infra_failures_excluded": 4,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:44:21Z",
      "losses": 116,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 68.72658602086715,
      "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": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 736,
      "rating_method": "sequential_elo",
      "raw_elo": 1855.1245626866132,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 83.8181052528922,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 522
    },
    {
      "admitted_plugins": 13,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:claude-opus-5:9f8812658c6b6343",
      "capped_draws": 0,
      "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": 81.94688975391686,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 66,
      "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": 158,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 61.97751151718376,
      "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": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 922,
      "rating_method": "sequential_elo",
      "raw_elo": 1838.6868412834826,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 77.80156217109193,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 698
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-5-6-sol:c051d828081d0d91",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 17
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 6.83719875,
        "mean": 5.427906484375001,
        "median": 5.376420937500001,
        "min": 4.5604125,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 17
        },
        "run_count": 16,
        "token_priced_attempt_count": 17,
        "total": 86.84650375
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 76.55089975602554,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 113,
      "eligibility_flag": true,
      "entry_count": 16,
      "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": 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": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 8,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T09:27:52Z",
      "losses": 276,
      "max_score": 99.52317300196941,
      "measured_at": null,
      "min_score": 53.00732553531228,
      "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": 1418,
      "rating_method": "sequential_elo",
      "raw_elo": 1766.2507666678293,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 76.55089975602554,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1029
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-5-4:6f2d7de576c6f541",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 18
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 2.44992,
        "mean": 2.0808053125,
        "median": 2.17314,
        "min": 1.325615,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 18
        },
        "run_count": 16,
        "token_priced_attempt_count": 18,
        "total": 33.292885
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 71.6443643604213,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 225,
      "eligibility_flag": true,
      "entry_count": 15,
      "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": 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": "2026-08-22T08:04:25Z",
      "losses": 195,
      "max_score": 96.95590676313576,
      "measured_at": null,
      "min_score": 37.76802152050538,
      "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": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1357,
      "rating_method": "sequential_elo",
      "raw_elo": 1777.7588136375048,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 71.6443643604213,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 937
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:claude-opus-4-8:ebbf2432c9a71c0d",
      "capped_draws": 0,
      "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": 68.9455842674663,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 89,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": "2026-08-05T04:35:38Z",
      "losses": 185,
      "max_score": 81.45539006883097,
      "measured_at": null,
      "min_score": 51.00200589427959,
      "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": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 690,
      "rating_method": "sequential_elo",
      "raw_elo": 1710.9049783822788,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 66.68197733259686,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 416
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-5-5:eb9fefeb3ace38a1",
      "capped_draws": 0,
      "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": 68.8969621273796,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 126,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": "2026-08-05T04:44:25Z",
      "losses": 147,
      "max_score": 92.32704029193545,
      "measured_at": null,
      "min_score": 27.370645611635616,
      "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": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 652,
      "rating_method": "sequential_elo",
      "raw_elo": 1757.292254161681,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 66.63495154439632,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 379
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:google-gemini-3-6-flash:3f9a827f3fe4c1e8",
      "capped_draws": 0,
      "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": 66.24088892568602,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 301,
      "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": "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",
        "GB2-07"
      ],
      "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": "2026-08-23T12:51:05Z",
      "losses": 484,
      "max_score": 90.98102138726986,
      "measured_at": null,
      "min_score": 47.781451793024814,
      "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": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1824,
      "rating_method": "sequential_elo",
      "raw_elo": 1691.5177738186753,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 61.644093105485865,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1039
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:x-ai-grok-4-5:b0a92c183e177d45",
      "capped_draws": 0,
      "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": 60.36479324487097,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 251,
      "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": "2026-08-23T09:27:52Z",
      "losses": 358,
      "max_score": 89.63424632680322,
      "measured_at": null,
      "min_score": 32.171720342982304,
      "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": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1294,
      "rating_method": "sequential_elo",
      "raw_elo": 1654.1768913068108,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 60.36479324487097,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 685
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-5-6-terra:8869a1009cce8005",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 11
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 12.137519999999999,
        "mean": 8.1660015625,
        "median": 8.18098,
        "min": 4.7142525,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 65.32801249999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 58.10431141243433,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 157,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "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": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 8,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:35:30Z",
      "losses": 234,
      "max_score": 72.91627837470821,
      "measured_at": null,
      "min_score": 41.410294640288974,
      "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": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 732,
      "rating_method": "sequential_elo",
      "raw_elo": 1632.4184387979212,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 58.10431141243433,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 341
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-5-6-luna:0e3f3e6646cbf8db",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 18
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.51553995,
        "mean": 0.34562851249999993,
        "median": 0.32314493749999995,
        "min": 0.21152055,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 18
        },
        "run_count": 17,
        "token_priced_attempt_count": 18,
        "total": 6.0079747999999995
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 52.99531550646229,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 363,
      "eligibility_flag": true,
      "entry_count": 16,
      "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": [
        "GB2-03"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.7777777777777778,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_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",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 8,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T08:55:05Z",
      "losses": 414,
      "max_score": 80.44715581991792,
      "measured_at": null,
      "min_score": 23.37892449322698,
      "model_code_failure_rate": 0.1111111111111111,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": 0.8888888888888888,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1409,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.9156954607508,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": 1,
      "repaired_rate": 0.1111111111111111,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 51.45757923484194,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 632
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:claude-sonnet-5:4c96a5e86d12d58b",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 18,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 19
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.48068,
        "mean": 0.36446575,
        "median": 0.3730325,
        "min": 0.22767700000000002,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 2,
          "boardgame-list-prices-2026-08-08": 17
        },
        "run_count": 18,
        "token_priced_attempt_count": 19,
        "total": 6.692412
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 49.75918410793966,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 479,
      "eligibility_flag": true,
      "entry_count": 18,
      "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": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 16,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T08:13:25Z",
      "losses": 554,
      "max_score": 61.83534732022994,
      "measured_at": null,
      "min_score": 24.11617014323098,
      "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": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1698,
      "rating_method": "sequential_elo",
      "raw_elo": 1560.0019131685872,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 49.75918410793966,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 665
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:google-gemini-3-5-flash:8820630a07e04d7e",
      "capped_draws": 0,
      "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": 0.6921525,
        "mean": 0.48907706250000005,
        "median": 0.483741,
        "min": 0.401826,
        "recorded_attempt_count": 18,
        "run_count": 8,
        "total": 3.9126165000000004
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 49.715987926047966,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 153,
      "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": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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"
      ],
      "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": "2026-08-05T05:04:52Z",
      "losses": 198,
      "max_score": 82.05588219794666,
      "measured_at": null,
      "min_score": 21.612048110556422,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": 0.75,
      "provider": "Google",
      "provider_key": "google",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 536,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.5978601956003,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 46.26593993904155,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 185
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-5:c96e6073f5cb5c2e",
      "capped_draws": 0,
      "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": 2.2561125000000004
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 45.95221951291531,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 236,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_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": 272,
      "max_score": 66.00620122264021,
      "measured_at": null,
      "min_score": 20.557432544949897,
      "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": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 758,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.2728230395546,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 45.95221951291531,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 250
    },
    {
      "admitted_plugins": 25,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:stealth-ox-alpha:650c74dfce556ee1",
      "capped_draws": 0,
      "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": 43.59998821261214,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 61,
      "eligibility_flag": true,
      "entry_count": 23,
      "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": "2026-08-23T15:12:59Z",
      "losses": 81,
      "max_score": 50.86244134919709,
      "measured_at": null,
      "min_score": 35.45001529607838,
      "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": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 333,
      "rating_method": "sequential_elo",
      "raw_elo": 1558.5303719528426,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 43.59998821261214,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 191
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:deepseek-deepseek-v4-pro:bda2de12b3bef61c",
      "capped_draws": 0,
      "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": 0.10909930499999998,
        "mean": 0.082847753875,
        "median": 0.084146916,
        "min": 0.03951746,
        "recorded_attempt_count": 16,
        "run_count": 8,
        "total": 0.662782031
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 46.78401626089681,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 140,
      "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": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": 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": "2026-08-05T05:11:41Z",
      "losses": 252,
      "max_score": 74.1333084252556,
      "measured_at": null,
      "min_score": 30.850811557145292,
      "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": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 598,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.3616732040919,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_literal_legacy",
          "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 43.53743286070221,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 206
    },
    {
      "admitted_plugins": 19,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:o3:908e4e2cf254357c",
      "capped_draws": 0,
      "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": 0.07737849999999999,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 40
        },
        "recorded_attempt_count": 32,
        "run_count": 32,
        "token_priced_attempt_count": 8,
        "total": 2.927552
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": 47.39906310459903,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 289,
      "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": "2026-08-23T13:45:04Z",
      "losses": 1289,
      "max_score": 56.64546823346215,
      "measured_at": null,
      "min_score": 38.84780628544275,
      "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": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2919,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.6166216918355,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 41.60740814708737,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1341
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:deepseek-deepseek-v4-flash:3321a752a2ed6366",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0221782524,
        "mean": 0.00999808046,
        "median": 0.009941171,
        "min": 0.00212373,
        "recorded_attempt_count": 14,
        "run_count": 8,
        "total": 0.07998464368
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.93877346153044,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 155,
      "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": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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"
      ],
      "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": "2026-08-05T04:43:54Z",
      "losses": 231,
      "max_score": 72.03816050961174,
      "measured_at": null,
      "min_score": 22.300174477766653,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": 0.75,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 560,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.0717561534093,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_literal_legacy",
          "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 37.167216649878206,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 174
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:google-gemini-3-5-flash-lite:abb2b9fa09f58cba",
      "capped_draws": 0,
      "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": 35.62010828184078,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 456,
      "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": "2026-08-23T09:38:06Z",
      "losses": 844,
      "max_score": 53.05834174786712,
      "measured_at": null,
      "min_score": 24.21600641424555,
      "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": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1855,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.4366336210078,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 34.45063637172133,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 555
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:openai-gpt-oss-120b:707f3723f9845847",
      "capped_draws": 0,
      "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": 0.01660212,
        "mean": 0.008820586750000001,
        "median": 0.007023681,
        "min": 0.00271606,
        "recorded_attempt_count": 19,
        "run_count": 8,
        "total": 0.07056469400000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.58212869949016,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 175,
      "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": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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",
        "GB2-05"
      ],
      "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": "2026-08-05T05:11:31Z",
      "losses": 157,
      "max_score": 67.82204727657161,
      "measured_at": null,
      "min_score": 13.91305101107773,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 3,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": 0.625,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 432,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.0618356661885,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 34.30490253088758,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 100
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:tencent-hy3-preview:cbb13c5a7417a861",
      "capped_draws": 0,
      "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": 36.126585006800155,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 157,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": 295,
      "max_score": 58.41330958645064,
      "measured_at": null,
      "min_score": 13.758406271721789,
      "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": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 648,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.9272087886864,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 33.92663550598933,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 196
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:xiaomi-mimo-v2-5:865be584a2f7aaf7",
      "capped_draws": 0,
      "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": 34.32762282883396,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 231,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 85,
      "max_score": 55.77389183234963,
      "measured_at": null,
      "min_score": 17.065325253973946,
      "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": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 364,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.8699538248118,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 30.522052436048757,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 9,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:671e21a17463ea94",
      "capped_draws": 0,
      "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": 34.73276605228333,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 342,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": 319,
      "max_score": 42.912176221849236,
      "measured_at": null,
      "min_score": 19.283288670132,
      "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": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 819,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.4469268933788,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 30.079457744979113,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 158
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:google-gemini-3-1-flash-lite:ff56b3b6c0d25588",
      "capped_draws": 0,
      "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": 33.039846973976665,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 136,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": 254,
      "max_score": 44.84292897073299,
      "measured_at": null,
      "min_score": 19.73749709047673,
      "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": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 485,
      "rating_method": "sequential_elo",
      "raw_elo": 1355.6660609099245,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 29.377039792329757,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:stepfun-step-3-7-flash:4da76a51b292ca95",
      "capped_draws": 0,
      "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": 31.867344410388103,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 78,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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": 265,
      "max_score": 42.18034696924738,
      "measured_at": null,
      "min_score": 12.522239497043625,
      "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": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 489,
      "rating_method": "sequential_elo",
      "raw_elo": 1347.4262428175327,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 28.33452120880606,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 146
    },
    {
      "admitted_plugins": 9,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:thinkingmachines-inkling:8db7573c02acc990",
      "capped_draws": 0,
      "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": 31.033557017137518,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 409,
      "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": "2026-08-23T09:56:43Z",
      "losses": 674,
      "max_score": 58.54870417164183,
      "measured_at": null,
      "min_score": 17.155695255029734,
      "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": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1350,
      "rating_method": "sequential_elo",
      "raw_elo": 1366.5464267245325,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 26.875848746633917,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 267
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:z-ai-glm-5-2:bc1714da76816a46",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 2,
        "cell_count": 1,
        "cost_basis_counts": {
          "provider_reported": 7
        },
        "evidence_basis": "Provider-reported",
        "max": 0.09063263032999999,
        "mean": 0.09063263032999999,
        "median": 0.09063263032999999,
        "min": 0.09063263032999999,
        "recorded_attempt_count": 7,
        "run_count": 2,
        "total": 0.18126526065999998
      },
      "codegen_evaluated_cells": 2,
      "conditional_success_score": 51.704133366709385,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 80,
      "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": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
        "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T14:35:20Z",
      "losses": 69,
      "max_score": 51.704133366709385,
      "measured_at": null,
      "min_score": 51.704133366709385,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1535.1007128451727,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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_literal_legacy",
          "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 51.704133366709385,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:meta-muse-spark-1-2:8ed12b9970d2209b",
      "capped_draws": 0,
      "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": 51.295019038484355,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 22,
      "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": [
        "below_generation_quality_threshold"
      ],
      "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": "2026-08-21T11:42:50Z",
      "losses": 71,
      "max_score": 53.82210709138648,
      "measured_at": null,
      "min_score": 48.767930985582225,
      "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": 182,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.459813823059,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 51.295019038484355,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:moonshotai-kimi-k3:6cfd7a6936cf4591",
      "capped_draws": 0,
      "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": 52.396363285760984,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 233,
      "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [
        "GB2-08"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T13:52:12Z",
      "losses": 193,
      "max_score": 80.31858860898552,
      "measured_at": null,
      "min_score": 23.676197661918458,
      "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": 756,
      "rating_method": "sequential_elo",
      "raw_elo": 1578.9701721531958,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 48.169166963777016,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 330
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:claude-opus-4-5:0dacb4d5b9cf9367",
      "capped_draws": 0,
      "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": 42.080323760465184,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 373,
      "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T04:11:45Z",
      "losses": 485,
      "max_score": 63.991356251926845,
      "measured_at": null,
      "min_score": 13.32462959183295,
      "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": 1328,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.674399443773,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 42.080323760465184,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:qwen-qwen3-8-max:83f392701e202fd4",
      "capped_draws": 0,
      "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": 43.31650489789862,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 36,
      "eligibility_flag": false,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [
        "GB2-02",
        "GB2-06",
        "GB2-08"
      ],
      "infra_failures_excluded": 3,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T12:51:05Z",
      "losses": 29,
      "max_score": 65.34857672458816,
      "measured_at": null,
      "min_score": 20.442652389870492,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 129,
      "rating_method": "sequential_elo",
      "raw_elo": 1554.971631815284,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 40.96622103853259,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:thinkingmachines-inkling-small:bbca5c562fb1ab46",
      "capped_draws": 0,
      "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": 36.52576900215633,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 44,
      "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": "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T03:04:42Z",
      "losses": 33,
      "max_score": 54.116030920939295,
      "measured_at": null,
      "min_score": 11.574430248545012,
      "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": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 117,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.4824455565315,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 34.543939546177654,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 0,
      "canonical_public_row_identity": "publication-row.v1:intensive:mistralai-mistral-medium-3-5:58c9456c0bd2ac32",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.3927285,
        "mean": 0.1902770625,
        "median": 0.16804049999999998,
        "min": 0.08751,
        "recorded_attempt_count": 14,
        "run_count": 9,
        "total": 1.914945
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 21.11214296718544,
      "contributing_entrants": null,
      "distinct_rated_opponents": 0,
      "draws": 19,
      "eligibility_flag": false,
      "entry_count": 4,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "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",
        "GB2-08"
      ],
      "first_pass_admitted": 2,
      "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": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:22:40Z",
      "losses": 265,
      "max_score": 28.20923732650551,
      "measured_at": null,
      "min_score": 11.379446013072632,
      "model_code_failure_rate": 0.5555555555555556,
      "model_code_failures": 5,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": 0.4444444444444444,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 366,
      "rating_method": "sequential_elo",
      "raw_elo": 1212.7803751480983,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "track",
      "score": 17.23799254876425,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 192,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01: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": 2,
      "distinct_rated_opponents": 89,
      "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": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-20T02:25:20Z",
      "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": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1997.4300020219584,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 96.95590676313576,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.025404183609156,
      "unilateral_faults": 0,
      "wins": 184
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 170,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:x-ai-grok-4-5:b0a92c183e177d45",
      "capped_draws": 32,
      "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": "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": 19,
      "max_score": null,
      "measured_at": "2026-08-23T08:55:05Z",
      "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": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1829.172240589223,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 80.96417402361442,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 119
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 188,
      "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": 2,
      "distinct_rated_opponents": 89,
      "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": 52,
      "max_score": null,
      "measured_at": "2026-08-23T08:55:05Z",
      "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": 1834.5344217203296,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 80.44715581991792,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.5830662995282605,
      "unilateral_faults": 0,
      "wins": 136
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:claude-fable-5:5a1cc0fafbb266c7",
      "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:38:01Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1824.3873130220802,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 79.58869492247467,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 196,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:gpt-5-6-sol:c051d828081d0d91",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 89,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 44,
      "max_score": null,
      "measured_at": "2026-08-22T09:15:53Z",
      "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": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1798.2420883252416,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 76.86094003829044,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 6.571294191973962,
      "unilateral_faults": 0,
      "wins": 149
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:gpt-5-5:eb9fefeb3ace38a1",
      "capped_draws": 30,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 30,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:28:59Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1756.676617437372,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 72.70600935658693,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 153,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:claude-opus-4-5:0dacb4d5b9cf9367",
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 26,
      "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": 36,
      "max_score": null,
      "measured_at": "2026-08-19T23:48:46Z",
      "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": 153,
      "rating_method": "sequential_elo",
      "raw_elo": 1662.883091394821,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 63.991356251926845,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 2,
      "attempted_matches": 128,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:claude-opus-5:9f8812658c6b6343",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 57,
      "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-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": 47,
      "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": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1660.4981048082484,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 61.97751151718376,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 18.466769200052298,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 192,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:claude-sonnet-5:4c96a5e86d12d58b",
      "capped_draws": 32,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 92,
      "draws": 32,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-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": 62,
      "max_score": null,
      "measured_at": "2026-08-22T14:45:05Z",
      "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": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1649.9903636318293,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 61.83534732022994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.090352872155288,
      "unilateral_faults": 0,
      "wins": 98
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 174,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:moonshotai-kimi-k3:6cfd7a6936cf4591",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "draws": 17,
      "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": 59,
      "max_score": null,
      "measured_at": "2026-08-19T23:39:50Z",
      "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": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1633.9448139210695,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 61.26830836120785,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 98
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:tencent-hy3-preview:cbb13c5a7417a861",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T13:20:55Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1614.8727554112447,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 58.41330958645064,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:claude-opus-4-8:ebbf2432c9a71c0d",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:35:46Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1609.684924746103,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 58.000169538136674,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 54
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 446,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:o3:908e4e2cf254357c",
      "capped_draws": 32,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 169,
      "draws": 32,
      "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": 161,
      "max_score": null,
      "measured_at": "2026-08-22T09:26:27Z",
      "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": 446,
      "rating_method": "sequential_elo",
      "raw_elo": 1590.752419913073,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 56.64546823346215,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 253
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:meta-muse-spark-1-2:8ed12b9970d2209b",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "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": "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": 37,
      "max_score": null,
      "measured_at": "2026-08-20T02:02:55Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1571.9644721957648,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 53.82210709138648,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 323,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:google-gemini-3-6-flash:3f9a827f3fe4c1e8",
      "capped_draws": 92,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 126,
      "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": "google/gemini-3.6-flash",
        "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": 117,
      "max_score": null,
      "measured_at": "2026-08-22T09:15:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 322,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.7173895347846,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 49.590003923577925,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 113
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:gpt-5:c96e6073f5cb5c2e",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 6,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:31:39Z",
      "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": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.6425409214996,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 47.822980600607565,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01: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": 21,
      "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": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-23T12:28:17Z",
      "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": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.8930518724999,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.48137058261478,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:deepseek-deepseek-v4-pro:bda2de12b3bef61c",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 19,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:29:26Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.8732003554912,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_literal_legacy",
          "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 42.10203075533094,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:gpt-5-6-terra:8869a1009cce8005",
      "capped_draws": 31,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 31,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:35:46Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.6406737765797,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.410294640288974,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:671e21a17463ea94",
      "capped_draws": 20,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "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": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:16:49Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.8528152679808,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.82037411124304,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:deepseek-deepseek-v4-flash:3321a752a2ed6366",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "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": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T23:53:31Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1353.1558761739786,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_literal_legacy",
          "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.797564014719292,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 140,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:google-gemini-3-5-flash-lite:abb2b9fa09f58cba",
      "capped_draws": 28,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 28,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 78,
      "max_score": null,
      "measured_at": "2026-08-23T09:38:06Z",
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1318.8398191425192,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.072445927965525,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 142,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:thinkingmachines-inkling:8db7573c02acc990",
      "capped_draws": 53,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 53,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 83,
      "max_score": null,
      "measured_at": "2026-08-23T09:56:43Z",
      "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": 1200.6961116510595,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 17.155695255029734,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:xiaomi-mimo-v2-5:865be584a2f7aaf7",
      "capped_draws": 41,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "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": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 29,
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1213.1687467409479,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 17.065325253973946,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:stepfun-step-3-7-flash:4da76a51b292ca95",
      "capped_draws": 6,
      "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:35:13Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1165.3075653397077,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 12.522239497043625,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:mistralai-mistral-medium-3-5:58c9456c0bd2ac32",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "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": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:16:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1152.0261703164747,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 11.379446013072632,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 158,
      "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": 2,
      "distinct_rated_opponents": 68,
      "draws": 28,
      "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": 11,
      "max_score": null,
      "measured_at": "2026-08-23T09:27:52Z",
      "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": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1822.4131382061005,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 99.52317300196941,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 12.553584189490259,
      "unilateral_faults": 0,
      "wins": 119
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:claude-opus-4-8:ebbf2432c9a71c0d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 32,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:22:25Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1739.7423942603561,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 81.45539006883097,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:claude-fable-5:5a1cc0fafbb266c7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 37,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:25:18Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1705.9057480073943,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 73.74954635252826,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 43
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 118,
      "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": 45,
      "draws": 38,
      "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": 21,
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1698.998209186365,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 70.34600839013916,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 20.806447728429966,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02: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": 36,
      "draws": 51,
      "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": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:25:22Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1621.61381435049,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.7169870956697,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 144,
      "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": 53,
      "draws": 72,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 24,
      "max_score": null,
      "measured_at": "2026-08-23T09:27:52Z",
      "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": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1594.752196706652,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 51.08735602238606,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:gpt-5-6-terra:8869a1009cce8005",
      "capped_draws": 0,
      "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": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:16:44Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1584.5440638410278,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.84121932685183,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 28,
      "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": 14,
      "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": "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": 1,
      "max_score": null,
      "measured_at": "2026-08-23T14:10:11Z",
      "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": 28,
      "rating_method": "sequential_elo",
      "raw_elo": 1595.1315475505453,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.45001529607838,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 85.34944487358055,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:xiaomi-mimo-v2-5:865be584a2f7aaf7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 11,
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.3343523013145,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 27.437307852969795,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "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": 38,
      "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": "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": 8,
      "max_score": null,
      "measured_at": "2026-08-15T01:45:06Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.463385992254,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.879776376230204,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 150,
      "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": 2,
      "distinct_rated_opponents": 68,
      "draws": 117,
      "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": 20,
      "max_score": null,
      "measured_at": "2026-08-23T06:52:36Z",
      "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": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.3769341262514,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 24.11617014323098,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 13.787528268864886,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 130,
      "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": 49,
      "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": "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": 12,
      "max_score": null,
      "measured_at": "2026-08-15T01:44:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.3344994862955,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 23.676197661918458,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 2,
      "attempted_matches": 154,
      "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": 2,
      "distinct_rated_opponents": 75,
      "draws": 133,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-08-22T08:14:35Z",
      "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": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.6954959964735,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 23.37892449322698,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 13.29230808923531,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:deepseek-deepseek-v4-flash:3321a752a2ed6366",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "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": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:25:13Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.442621444907,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_literal_legacy",
          "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 22.300174477766653,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:gpt-5:c96e6073f5cb5c2e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 58,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T08:04:56Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.072947000906,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 20.557432544949897,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 17,
      "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": 9,
      "draws": 13,
      "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": 1,
      "max_score": null,
      "measured_at": "2026-08-23T05:29:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.2581453563312,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 20.442652389870492,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 74.10113019775793,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "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": 43,
      "draws": 111,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-08-22T14:35:05Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.031259226249,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.990967262210003,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 138,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:671e21a17463ea94",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 68,
      "draws": 118,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T08:44:46Z",
      "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": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.6237702694034,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.283288670132,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 16.016004726288628,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:openai-gpt-oss-120b:707f3723f9845847",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 59,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:23:18Z",
      "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": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.0685143240635,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 13.91305101107773,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:tencent-hy3-preview:cbb13c5a7417a861",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "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": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T05:07:08Z",
      "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": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.0591535680944,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 13.758406271721789,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 2,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 130,
      "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": 50,
      "draws": 107,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-08-19T22:29:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.2065730933373,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 13.32462959183295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 16,
      "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": 9,
      "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-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": 1,
      "max_score": null,
      "measured_at": "2026-08-23T03:04:42Z",
      "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": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.473546162997,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 11.574430248545012,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 116,
      "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": 50,
      "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": 9,
      "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": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1896.2197178100707,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 98.71900811266804,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 107
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:google-gemini-3-6-flash:3f9a827f3fe4c1e8",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "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": "google/gemini-3.6-flash",
        "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": 23,
      "max_score": null,
      "measured_at": "2026-08-22T17:46:24Z",
      "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": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1772.0196909880037,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 83.98010770719294,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 88
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 162,
      "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": 2,
      "distinct_rated_opponents": 72,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-21T15:52:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1747.1374541252894,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 79.44499279291648,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.84333382310696,
      "unilateral_faults": 0,
      "wins": 122
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:claude-fable-5:5a1cc0fafbb266c7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 32,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:08:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1699.478327839778,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 72.45110481946428,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:gpt-5-6-terra:8869a1009cce8005",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T22:43:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1614.760774095997,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 60.60474629403735,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2,
      "attempted_matches": 264,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:google-gemini-3-5-flash-lite:abb2b9fa09f58cba",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 97,
      "draws": 61,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 95,
      "max_score": null,
      "measured_at": "2026-08-22T20:25:22Z",
      "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": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1543.7025318084882,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 53.05834174786712,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.48567977499789805,
      "unilateral_faults": 0,
      "wins": 108
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:z-ai-glm-5-2:bc1714da76816a46",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 86,
      "draws": 80,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-22T14:35:20Z",
      "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": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1535.1007128451727,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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_literal_legacy",
          "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 51.704133366709385,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.3379525022706273,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 83,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:gpt-5-5:eb9fefeb3ace38a1",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 30,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:17:00Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.349657382233,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 49.85325759783324,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:meta-muse-spark-1-2:8ed12b9970d2209b",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": 34,
      "max_score": null,
      "measured_at": "2026-08-21T11:42:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.9551554503532,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 48.767930985582225,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:google-gemini-3-5-flash:8820630a07e04d7e",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "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": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:18:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.688890303186,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 47.29777519993979,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 420,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:claude-sonnet-5:4c96a5e86d12d58b",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 179,
      "draws": 165,
      "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": 127,
      "max_score": null,
      "measured_at": "2026-08-21T05:32:06Z",
      "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": 420,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.8216008851805,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.8105199390742,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 10.330972380580388,
      "unilateral_faults": 0,
      "wins": 128
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:thinkingmachines-inkling-small:bbca5c562fb1ab46",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 8,
      "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": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-22T14:35:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.532411443232,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.53778410260007,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 70.95786693528086,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 17,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03: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": 9,
      "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-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": 7,
      "max_score": null,
      "measured_at": "2026-08-22T21:12:16Z",
      "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": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.0917022516862,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.72942915084835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 74.10113019775793,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 158,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:x-ai-grok-4-5:b0a92c183e177d45",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "draws": 68,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 56,
      "max_score": null,
      "measured_at": "2026-08-22T23:22:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.345041387723,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.15892215398935,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:thinkingmachines-inkling:8db7573c02acc990",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 50,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-08-23T03:05:15Z",
      "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": 1455.6626650012568,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.92223596271898,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 77,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:gpt-5:c96e6073f5cb5c2e",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 29,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T03:06:54Z",
      "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": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.2318976814317,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.527524812029206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 1,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 152,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:claude-opus-4-5:0dacb4d5b9cf9367",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 41,
      "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": 64,
      "max_score": null,
      "measured_at": "2026-08-21T05:32:06Z",
      "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": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.6013043122741,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.20269156862466,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "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": 47,
      "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": "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": 55,
      "max_score": null,
      "measured_at": "2026-08-22T21:12:16Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.0846957731926,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.84780628544275,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:moonshotai-kimi-k3:6cfd7a6936cf4591",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 35,
      "max_score": null,
      "measured_at": "2026-08-22T13:52:12Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.701374575963,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.53169274626354,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 28
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 157,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:gpt-5-4:6f2d7de576c6f541",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 72,
      "draws": 45,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "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": 56,
      "max_score": null,
      "measured_at": "2026-08-21T11:43:42Z",
      "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": 155,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.7517819863665,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.76802152050538,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 13.774738137215436,
      "unilateral_faults": 2,
      "wins": 54
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 39,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03: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": 18,
      "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": "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": 8,
      "max_score": null,
      "measured_at": "2026-08-23T15:12:59Z",
      "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": 35,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.2407303398938,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.63978744841054,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 96.61669937087152,
      "unilateral_faults": 4,
      "wins": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 158,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:gpt-5-6-luna:0e3f3e6646cbf8db",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 75,
      "draws": 66,
      "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": 63,
      "max_score": null,
      "measured_at": "2026-08-22T12:02:27Z",
      "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": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.4189111847174,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.722469385399606,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 12.553584189490259,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:claude-fable-5:5a1cc0fafbb266c7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "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-fable-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:29:18Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1871.3393976382893,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 164,
      "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": 68,
      "draws": 26,
      "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": 19,
      "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": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1769.8664441103872,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 83.8367732821356,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.144085005109797,
      "unilateral_faults": 0,
      "wins": 119
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 152,
      "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": 58,
      "draws": 47,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 19,
      "max_score": null,
      "measured_at": "2026-08-22T06:50:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1735.222095654677,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 80.31858860898552,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 2,
      "attempted_matches": 176,
      "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": 2,
      "distinct_rated_opponents": 80,
      "draws": 52,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-22T05:58:30Z",
      "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": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1736.262097079852,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 78.91168626964662,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.5031429046309,
      "unilateral_faults": 0,
      "wins": 116
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:claude-opus-4-8:ebbf2432c9a71c0d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 37,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:29:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1645.9101696696405,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 65.49748409048952,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 181,
      "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": 2,
      "distinct_rated_opponents": 80,
      "draws": 79,
      "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": 28,
      "max_score": null,
      "measured_at": "2026-08-22T04:12:35Z",
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1619.9798243524701,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 61.22868483056382,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.074719125763062,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 305,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:google-gemini-3-6-flash:3f9a827f3fe4c1e8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 115,
      "draws": 77,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "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": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-23T12:51:05Z",
      "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": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1595.56223467484,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 58.999575365642215,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 135
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:gpt-5-6-terra:8869a1009cce8005",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 44,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:35:30Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1568.1292217619282,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 53.506645149871794,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 160,
      "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": 2,
      "distinct_rated_opponents": 77,
      "draws": 94,
      "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": 24,
      "max_score": null,
      "measured_at": "2026-08-22T06:51:00Z",
      "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": 160,
      "rating_method": "sequential_elo",
      "raw_elo": 1568.5761718074618,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 53.04143463463096,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.920326830426156,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "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": 11,
      "draws": 10,
      "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": 1,
      "max_score": null,
      "measured_at": "2026-08-23T12:51:05Z",
      "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": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1594.1909851365033,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.427853739274326,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 17,
      "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": 8,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 1,
      "max_score": null,
      "measured_at": "2026-08-22T17:44:30Z",
      "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": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1562.2633173996858,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.49159171005959,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 74.10113019775793,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "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": 24,
      "draws": 17,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-08-23T12:27:48Z",
      "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": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.063493316194,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.756439517176496,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:google-gemini-3-1-flash-lite:ff56b3b6c0d25588",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "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": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:05:18Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.643674866353,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.94245051776638,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:xiaomi-mimo-v2-5:865be584a2f7aaf7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 52,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 10,
      "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": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.8209858823616,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.63045169882911,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "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": 53,
      "draws": 84,
      "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": 22,
      "max_score": null,
      "measured_at": "2026-08-22T23:41:33Z",
      "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": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.2686847664681,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.504702920191605,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:openai-gpt-oss-120b:707f3723f9845847",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "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": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:11:31Z",
      "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": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.2518107556666,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.431761090888465,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:gpt-5:c96e6073f5cb5c2e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 68,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:05:23Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.7924746051574,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.423521122325184,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:671e21a17463ea94",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 65,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:29:54Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.9284785190819,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 37.17290928698389,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:deepseek-deepseek-v4-pro:bda2de12b3bef61c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "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": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:11:41Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.4828868208863,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_literal_legacy",
          "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.42341278591467,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 273,
      "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": 107,
      "draws": 171,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": 66,
      "max_score": null,
      "measured_at": "2026-08-22T23:41:33Z",
      "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": 272,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.685284464945,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 36.183653647643865,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 2,
      "attempted_matches": 164,
      "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": 2,
      "distinct_rated_opponents": 78,
      "draws": 88,
      "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": 48,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:21Z",
      "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": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.1703609820988,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.835204403454306,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.180010894095469,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 159,
      "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": 60,
      "draws": 83,
      "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": 59,
      "max_score": null,
      "measured_at": "2026-08-22T04:11:45Z",
      "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": 159,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.887567292159,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 35.688547830022806,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:google-gemini-3-5-flash:8820630a07e04d7e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "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": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:04:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.4852159713996,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 33.44484317358223,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 154,
      "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": 59,
      "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": "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": 54,
      "max_score": null,
      "measured_at": "2026-08-23T02:43:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.3352985192469,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.171720342982304,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:tencent-hy3-preview:cbb13c5a7417a861",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T05:11:51Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.305372108474,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.89937377831447,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:gpt-5-5:eb9fefeb3ace38a1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 45,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:29:50Z",
      "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": 1398.6125264834243,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 27.370645611635616,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:claude-fable-5:5a1cc0fafbb266c7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:52:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 2023.8636251018338,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 91.20233840190105,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 188,
      "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": 2,
      "distinct_rated_opponents": 87,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-08-22T08:04:25Z",
      "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": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 2021.4498788973235,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 90.89912695137986,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 179
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 140,
      "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": 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-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": 22,
      "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": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1976.177267738965,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 86.6055678570907,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 118
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:gpt-5-5:eb9fefeb3ace38a1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:40:01Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1927.4799055461476,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 83.16542149104123,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 288,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:google-gemini-3-6-flash:3f9a827f3fe4c1e8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 111,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "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": 44,
      "max_score": null,
      "measured_at": "2026-08-20T05:43:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 288,
      "rating_method": "sequential_elo",
      "raw_elo": 1918.3075744153398,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 82.98344935650789,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 244
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:deepseek-deepseek-v4-pro:bda2de12b3bef61c",
      "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": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:40:18Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1818.7116137409091,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_literal_legacy",
          "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 74.1333084252556,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 142,
      "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": 56,
      "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": 41,
      "max_score": null,
      "measured_at": "2026-08-22T10:31:06Z",
      "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": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1780.9418496208198,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 71.55758103790589,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 2,
      "attempted_matches": 182,
      "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": 2,
      "distinct_rated_opponents": 87,
      "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": 57,
      "max_score": null,
      "measured_at": "2026-08-15T00:19:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 182,
      "rating_method": "sequential_elo",
      "raw_elo": 1697.150154488464,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 63.91279578997471,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.399405802287859,
      "unilateral_faults": 0,
      "wins": 125
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:gpt-5:c96e6073f5cb5c2e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T22:34:38Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1681.8135849530192,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 62.830767356755665,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:gpt-5-6-terra:8869a1009cce8005",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:40:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1679.100259521219,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 62.53998912556835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:tencent-hy3-preview:cbb13c5a7417a861",
      "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": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T08:44:47Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1628.3276946126373,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 58.289597890358415,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 202,
      "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": 2,
      "distinct_rated_opponents": 96,
      "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": 92,
      "max_score": null,
      "measured_at": "2026-08-23T07:22:40Z",
      "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": 1607.8454582553452,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 56.6666251213187,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 5.845115932657641,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 196,
      "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": 2,
      "distinct_rated_opponents": 93,
      "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": 92,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:47Z",
      "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": 1553.3847277464513,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.09853206595015,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 6.532690756236184,
      "unilateral_faults": 0,
      "wins": 104
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:google-gemini-3-5-flash:8820630a07e04d7e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T10:18:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.7470805088597,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 52.08084603218233,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:deepseek-deepseek-v4-flash:3321a752a2ed6366",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:16:36Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1549.0224155741603,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_literal_legacy",
          "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 51.803795837193945,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:claude-opus-4-8:ebbf2432c9a71c0d",
      "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-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:57:20Z",
      "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": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.317407962045,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 51.00200589427959,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 4,
      "attempted_matches": 634,
      "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": 232,
      "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": 292,
      "max_score": null,
      "measured_at": "2026-08-23T13:45:04Z",
      "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": 634,
      "rating_method": "sequential_elo",
      "raw_elo": 1525.5655874239144,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.49609918819178,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 342
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 200,
      "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": 67,
      "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": 86,
      "max_score": null,
      "measured_at": "2026-08-20T05:43:17Z",
      "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": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.738619126404,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 49.55470457849347,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 114
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "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": 24,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-08-23T14:10:47Z",
      "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": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1571.444849455973,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 48.8825630594869,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 22,
      "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": 11,
      "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": 9,
      "max_score": null,
      "measured_at": "2026-08-22T11:34:23Z",
      "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": 22,
      "rating_method": "sequential_elo",
      "raw_elo": 1528.9563415565945,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.48436747017905,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 60.5072070285374,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 17,
      "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": 9,
      "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": 8,
      "max_score": null,
      "measured_at": "2026-08-20T12:56:07Z",
      "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": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.5327853795927,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.47012582547535,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 74.10113019775793,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 210,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:671e21a17463ea94",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 102,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:09:03Z",
      "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": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.4480042293753,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 42.912176221849236,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 4.89396709107023,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:stepfun-step-3-7-flash:4da76a51b292ca95",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T10:09:34Z",
      "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": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.1003871142666,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.604671181441674,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:mistralai-mistral-medium-3-5:58c9456c0bd2ac32",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:39:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1231.6665190864155,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 25.241466318726623,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 300,
      "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": 105,
      "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": 222,
      "max_score": null,
      "measured_at": "2026-08-22T23:45:14Z",
      "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": 300,
      "rating_method": "sequential_elo",
      "raw_elo": 1209.9376686322128,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 24.21600641424555,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:google-gemini-3-1-flash-lite:ff56b3b6c0d25588",
      "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:53:07Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1165.8540579796686,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.73749709047673,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 320,
      "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": 112,
      "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": 250,
      "max_score": null,
      "measured_at": "2026-08-22T23:41:42Z",
      "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": 1139.8966108091176,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 18.48372816664021,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 2,
      "attempted_matches": 314,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:google-gemini-3-6-flash:3f9a827f3fe4c1e8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 124,
      "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": "google/gemini-3.6-flash",
        "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": 46,
      "max_score": null,
      "measured_at": "2026-08-23T03:04:24Z",
      "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": 314,
      "rating_method": "sequential_elo",
      "raw_elo": 1969.472492857064,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 90.98102138726986,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 254
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 180,
      "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": 2,
      "distinct_rated_opponents": 82,
      "draws": 13,
      "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": 13,
      "max_score": null,
      "measured_at": "2026-08-20T17:51:34Z",
      "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": 180,
      "rating_method": "sequential_elo",
      "raw_elo": 1955.9990288949302,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 88.93765075471762,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.749961355672497,
      "unilateral_faults": 0,
      "wins": 154
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:claude-fable-5:5a1cc0fafbb266c7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 9,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:01:50Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1909.8483590250705,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 84.82657150590221,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:gpt-5-5:eb9fefeb3ace38a1",
      "capped_draws": 0,
      "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": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T14:42:32Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1909.8196476234893,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 84.82408848503748,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 63
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 176,
      "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": 2,
      "distinct_rated_opponents": 83,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 24,
      "max_score": null,
      "measured_at": "2026-08-21T05:32:10Z",
      "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": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1903.5767486670418,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 84.36878169555632,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.259934288992827,
      "unilateral_faults": 0,
      "wins": 143
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:google-gemini-3-5-flash:8820630a07e04d7e",
      "capped_draws": 0,
      "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:25:28Z",
      "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": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1877.810620435143,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 82.05588219794666,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 62
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 176,
      "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": 2,
      "distinct_rated_opponents": 80,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 31,
      "max_score": null,
      "measured_at": "2026-08-22T20:09:21Z",
      "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": 175,
      "rating_method": "sequential_elo",
      "raw_elo": 1833.5180772796284,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 78.29991891467037,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.405127205681364,
      "unilateral_faults": 0,
      "wins": 126
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:claude-opus-4-8:ebbf2432c9a71c0d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "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-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T23:53:43Z",
      "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": 1827.373724966149,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 77.69399608634865,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:gpt-5-6-terra:8869a1009cce8005",
      "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": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:37:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1762.4255362201798,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 72.24215339252389,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:openai-gpt-oss-120b:707f3723f9845847",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "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": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T11:32:58Z",
      "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": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1712.237284828002,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 67.82204727657161,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:gpt-5:c96e6073f5cb5c2e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 9,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T13:30:44Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1690.7719660077682,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 66.00620122264021,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 178,
      "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": 64,
      "draws": 17,
      "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": 71,
      "max_score": null,
      "measured_at": "2026-08-20T18:12:10Z",
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1601.6726322378718,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 59.34143229501704,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 156,
      "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": 54,
      "draws": 8,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-08-22T13:31:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1594.5323147640372,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 58.54870417164183,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:xiaomi-mimo-v2-5:865be584a2f7aaf7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 30,
      "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": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1577.339884678403,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 55.77389183234963,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "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": 9,
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-22T19:42:16Z",
      "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": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1608.3676756467582,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.116030920939295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 182,
      "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": 65,
      "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": "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": 82,
      "max_score": null,
      "measured_at": "2026-08-23T08:13:25Z",
      "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": 182,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.3129835742382,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.06333802227879,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 3,
      "attempted_matches": 42,
      "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": 21,
      "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": "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": 8,
      "max_score": null,
      "measured_at": "2026-08-23T12:25:25Z",
      "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": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1577.0114222032025,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 50.86244134919709,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 591,
      "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": 205,
      "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": "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": 286,
      "max_score": null,
      "measured_at": "2026-08-23T04:58:48Z",
      "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": 591,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.5307015706844,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 49.13258160734104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 288
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 15,
      "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": 9,
      "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": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-22T16:31:50Z",
      "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": 15,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.7378338885317,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.45237289235433,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 81.25,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 188,
      "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": 2,
      "distinct_rated_opponents": 87,
      "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-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": 99,
      "max_score": null,
      "measured_at": "2026-08-23T08:13:25Z",
      "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": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.7537777777416,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.84440293052995,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.557446496601106,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 294,
      "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": 106,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "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": 152,
      "max_score": null,
      "measured_at": "2026-08-23T00:33:30Z",
      "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": 294,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.0497650366196,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.75966543731385,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 129
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:stepfun-step-3-7-flash:4da76a51b292ca95",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:01:30Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1412.0094597124114,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 42.18034696924738,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:deepseek-deepseek-v4-pro:bda2de12b3bef61c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T23:08:34Z",
      "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": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1399.9603695080434,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_literal_legacy",
          "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 41.31141247367678,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 91,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:671e21a17463ea94",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T23:17:48Z",
      "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": 91,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.9558533954528,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.27021537575938,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.378603514268699,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:deepseek-deepseek-v4-flash:3321a752a2ed6366",
      "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": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:53:03Z",
      "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": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1269.9135910657938,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_literal_legacy",
          "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.52707950589016,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 95,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:google-gemini-3-1-flash-lite:ff56b3b6c0d25588",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:35:51Z",
      "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": 95,
      "rating_method": "sequential_elo",
      "raw_elo": 1265.0077154404437,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 29.280934011909366,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.281036307982882,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:mistralai-mistral-medium-3-5:58c9456c0bd2ac32",
      "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": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:35:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1253.7221512485582,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 28.20923732650551,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:tencent-hy3-preview:cbb13c5a7417a861",
      "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": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:52:58Z",
      "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": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1236.8815002319625,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.752823304656847,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "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": 37,
      "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": "2026-08-05T04:22:40Z",
      "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": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 2071.119577926703,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:gpt-5-5:eb9fefeb3ace38a1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:35:52Z",
      "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": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1985.8838134621776,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 92.32704029193545,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 194,
      "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": 2,
      "distinct_rated_opponents": 87,
      "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": 18,
      "max_score": null,
      "measured_at": "2026-08-19T21:21:29Z",
      "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": 194,
      "rating_method": "sequential_elo",
      "raw_elo": 1930.5533799880245,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 87.10047490567965,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 6.759599509820776,
      "unilateral_faults": 0,
      "wins": 176
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:claude-opus-4-8:ebbf2432c9a71c0d",
      "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:35:38Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1824.9248359828734,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 77.1003159963057,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 188,
      "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": 2,
      "distinct_rated_opponents": 87,
      "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": 31,
      "max_score": null,
      "measured_at": "2026-08-23T08:55:50Z",
      "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": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1817.2716653984826,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 76.37750292453808,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.5830662995282605,
      "unilateral_faults": 0,
      "wins": 157
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 186,
      "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": 2,
      "distinct_rated_opponents": 87,
      "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": 49,
      "max_score": null,
      "measured_at": "2026-08-22T06:40:22Z",
      "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": 186,
      "rating_method": "sequential_elo",
      "raw_elo": 1789.226380256292,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 73.71875066727475,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.840775046388435,
      "unilateral_faults": 0,
      "wins": 137
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:gpt-5-6-terra:8869a1009cce8005",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:18:27Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1780.4659593446845,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 72.91627837470821,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:deepseek-deepseek-v4-flash:3321a752a2ed6366",
      "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": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:42:46Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1770.709939839599,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_literal_legacy",
          "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 72.03816050961174,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:claude-fable-5:5a1cc0fafbb266c7",
      "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:43:03Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1735.946996477361,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 68.72658602086715,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "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": 8,
      "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": 0,
      "max_score": null,
      "measured_at": "2026-08-22T06:40:22Z",
      "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": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1746.3008626110957,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 65.34857672458816,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 166,
      "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": 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": "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": 62,
      "max_score": null,
      "measured_at": "2026-08-23T02:23:52Z",
      "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": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1657.3711692973993,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 62.28100802900767,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 104
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:google-gemini-3-5-flash:8820630a07e04d7e",
      "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": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T22:51:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1663.7552103873281,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 61.804532842080334,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 180,
      "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": 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": "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": 68,
      "max_score": null,
      "measured_at": "2026-08-19T21:33:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 180,
      "rating_method": "sequential_elo",
      "raw_elo": 1612.648077127973,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 58.18702905042954,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 112
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:gpt-5:c96e6073f5cb5c2e",
      "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T15:11:05Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.540591357989,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 57.24690808187588,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 200,
      "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": 2,
      "distinct_rated_opponents": 93,
      "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": 79,
      "max_score": null,
      "measured_at": "2026-08-22T23:00:29Z",
      "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": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1602.9817039067634,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 56.320806353852134,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 6.1194494987894155,
      "unilateral_faults": 0,
      "wins": 121
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:deepseek-deepseek-v4-pro:bda2de12b3bef61c",
      "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": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:16:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1598.2368673537846,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_literal_legacy",
          "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 55.8831215680576,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 162,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:google-gemini-3-6-flash:3f9a827f3fe4c1e8",
      "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": "google/gemini-3.6-flash",
        "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": 74,
      "max_score": null,
      "measured_at": "2026-08-22T19:11:52Z",
      "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": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.6788239490022,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 47.781451793024814,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 2,
      "attempted_matches": 170,
      "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": 61,
      "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": 77,
      "max_score": null,
      "measured_at": "2026-08-19T21:21:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.1314410426282,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 47.705624366124106,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 3,
      "attempted_matches": 48,
      "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": 24,
      "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": 17,
      "max_score": null,
      "measured_at": "2026-08-23T14:09:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1557.9397208469782,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 46.70643609553631,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 636,
      "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": 235,
      "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": 350,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 636,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.1447162410047,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 45.16236630356082,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 286
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:google-gemini-3-1-flash-lite:ff56b3b6c0d25588",
      "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:09:18Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.7936186306395,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.84292897073299,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 36
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 315,
      "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": 116,
      "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": 162,
      "max_score": null,
      "measured_at": "2026-08-23T08:13:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 315,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.2642846072872,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.78344638910896,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 153
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:openai-gpt-oss-120b:707f3723f9845847",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T01:17:39Z",
      "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": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.4652985743849,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 39.64119866533117,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 101,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:stepfun-step-3-7-flash:4da76a51b292ca95",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:50:20Z",
      "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": 101,
      "rating_method": "sequential_elo",
      "raw_elo": 1349.1712838775788,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.46189477313855,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 5.757377148833722,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 174,
      "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": 66,
      "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": 129,
      "max_score": null,
      "measured_at": "2026-08-22T06:50:33Z",
      "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": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1268.3605173911951,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 25.73846555139435,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:tencent-hy3-preview:cbb13c5a7417a861",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:12:54Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1276.1948853703204,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 25.647698335291103,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 16,
      "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": 9,
      "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": 15,
      "max_score": null,
      "measured_at": "2026-08-19T21:57:24Z",
      "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": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1304.7852176135736,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 22.881993246353847,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:mistralai-mistral-medium-3-5:58c9456c0bd2ac32",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:22:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1213.7066599409454,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 19.618422210437004,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:claude-fable-5:5a1cc0fafbb266c7",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "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",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:44:21Z",
      "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": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 2070.226734381098,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 178,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:x-ai-grok-4-5:b0a92c183e177d45",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 68,
      "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": "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": 20,
      "max_score": null,
      "measured_at": "2026-08-22T17:44:01Z",
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1958.1843507591848,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 89.63424632680322,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 156
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 174,
      "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": 77,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:44:12Z",
      "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": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1797.9285674036369,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 72.14335911820079,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.552760371103872,
      "unilateral_faults": 0,
      "wins": 135
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-5-5:eb9fefeb3ace38a1",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:44:25Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1793.2236111969223,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 72.03227205758726,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:claude-opus-4-8:ebbf2432c9a71c0d",
      "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": "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:22:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1792.3813910887834,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 71.86972819787296,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 192,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:claude-sonnet-5:4c96a5e86d12d58b",
      "capped_draws": 55,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 91,
      "draws": 55,
      "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": 51,
      "max_score": null,
      "measured_at": "2026-08-23T02:42:42Z",
      "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": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1656.130025467018,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 58.006259476018926,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.090352872155288,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 188,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-5-4:6f2d7de576c6f541",
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 90,
      "draws": 37,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-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": 54,
      "max_score": null,
      "measured_at": "2026-08-15T02:22:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1632.292798608477,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 55.54806206171865,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.686045325052198,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-5-6-terra:8869a1009cce8005",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:23:24Z",
      "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": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1623.2810218217542,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 54.77316499562428,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 180,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-5-6-sol:c051d828081d0d91",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 85,
      "draws": 13,
      "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": 69,
      "max_score": null,
      "measured_at": "2026-08-23T02:42:42Z",
      "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": 180,
      "rating_method": "sequential_elo",
      "raw_elo": 1607.952787052161,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 53.00732553531228,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.673739368419632,
      "unilateral_faults": 0,
      "wins": 98
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 314,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:google-gemini-3-6-flash:3f9a827f3fe4c1e8",
      "capped_draws": 107,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 124,
      "draws": 107,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "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": 90,
      "max_score": null,
      "measured_at": "2026-08-22T23:22:38Z",
      "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": 314,
      "rating_method": "sequential_elo",
      "raw_elo": 1561.8662103116926,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 49.370612946586476,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 3,
      "attempted_matches": 478,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:o3:908e4e2cf254357c",
      "capped_draws": 191,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 188,
      "draws": 191,
      "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": 145,
      "max_score": null,
      "measured_at": "2026-08-22T14:19:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 478,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.6216092291434,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 44.110057009595636,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 3,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:stealth-ox-alpha:650c74dfce556ee1",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 21,
      "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": "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": 7,
      "max_score": null,
      "measured_at": "2026-08-23T14:12:04Z",
      "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": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1570.5181600374551,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 43.02085235239664,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 182,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-5-6-luna:0e3f3e6646cbf8db",
      "capped_draws": 58,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 88,
      "draws": 58,
      "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": 66,
      "max_score": null,
      "measured_at": "2026-08-21T18:10:38Z",
      "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": 182,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.916458011123,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 40.89347524643575,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.399405802287859,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:tencent-hy3-preview:cbb13c5a7417a861",
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "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": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-03T12:45:25Z",
      "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": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.8491002180717,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 38.12488588080784,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-5:c96e6073f5cb5c2e",
      "capped_draws": 66,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "draws": 66,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-04T23:45:21Z",
      "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": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.3165817886681,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 34.20242036213885,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 17,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:thinkingmachines-inkling-small:bbca5c562fb1ab46",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 8,
      "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": "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": 1,
      "max_score": null,
      "measured_at": "2026-08-22T23:00:21Z",
      "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": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.4221652498795,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 33.608426961121125,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 74.10113019775793,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:qwen-qwen3-8-max:83f392701e202fd4",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 8,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "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": 4,
      "max_score": null,
      "measured_at": "2026-08-23T02:42:56Z",
      "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": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.2655519062441,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.3302819181756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 70.95786693528086,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:deepseek-deepseek-v4-flash:3321a752a2ed6366",
      "capped_draws": 77,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 77,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:43:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.1860928220167,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_literal_legacy",
          "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.16586642400081,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:openai-gpt-oss-120b:707f3723f9845847",
      "capped_draws": 67,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "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": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:53:14Z",
      "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": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1400.2862698488254,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 32.10258545358184,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 196,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:671e21a17463ea94",
      "capped_draws": 132,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 95,
      "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": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:29:22Z",
      "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": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1397.872639678978,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 31.93763264773245,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 6.571294191973962,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:deepseek-deepseek-v4-pro:bda2de12b3bef61c",
      "capped_draws": 65,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 65,
      "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T04:23:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1387.905101445435,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_literal_legacy",
          "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.850811557145292,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:xiaomi-mimo-v2-5:865be584a2f7aaf7",
      "capped_draws": 71,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "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": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": 5,
      "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": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1390.6857995210323,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.7311375060473,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:stepfun-step-3-7-flash:4da76a51b292ca95",
      "capped_draws": 70,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 70,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T00:38:29Z",
      "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": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1385.5425180436987,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.56756963106926,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:google-gemini-3-1-flash-lite:ff56b3b6c0d25588",
      "capped_draws": 72,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 72,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T02:15:42Z",
      "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": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1381.0312376325182,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 30.395424278997872,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "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": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 186,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:claude-opus-4-5:0dacb4d5b9cf9367",
      "capped_draws": 99,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 65,
      "draws": 99,
      "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": 70,
      "max_score": null,
      "measured_at": "2026-08-21T15:41:34Z",
      "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": 186,
      "rating_method": "sequential_elo",
      "raw_elo": 1346.2739670506865,
      "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 27.83360360167963,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 178,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:thinkingmachines-inkling:8db7573c02acc990",
      "capped_draws": 103,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 103,
      "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": 71,
      "max_score": null,
      "measured_at": "2026-08-21T19:14:04Z",
      "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": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1337.923250186877,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.923956847273455,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 170,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:google-gemini-3-5-flash-lite:abb2b9fa09f58cba",
      "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": "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": 61,
      "max_score": null,
      "measured_at": "2026-08-21T18:21:11Z",
      "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": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1329.5503292837363,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 26.007530314351136,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_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": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:google-gemini-3-5-flash:8820630a07e04d7e",
      "capped_draws": 62,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 62,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_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": "2026-08-05T03:58:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1296.1001435676862,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_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_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": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "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": "gb2-20260823-7d5648862dc8",
      "row_kind": "game",
      "score": 21.612048110556422,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260823_205116",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 0
    }
  ],
  "schema_version": 11,
  "snapshot_id": "20260823_205116",
  "suite_line_id": "gamebench2",
  "suite_version": "2-known8-r3"
}